<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Gosia on Medium]]></title>
        <description><![CDATA[Stories by Gosia on Medium]]></description>
        <link>https://medium.com/@gosiai?source=rss-7adfacbbf591------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*OyH_av-W5FAXhLsgKubQFA@2x.jpeg</url>
            <title>Stories by Gosia on Medium</title>
            <link>https://medium.com/@gosiai?source=rss-7adfacbbf591------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Tue, 17 Nov 2026 20:56:30 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@gosiai/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Get started with Cognitive Services]]></title>
            <link>https://medium.com/@gosiai/get-started-with-cognitive-services-4d55b734e082?source=rss-7adfacbbf591------2</link>
            <guid isPermaLink="false">https://medium.com/p/4d55b734e082</guid>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[cognitive-services]]></category>
            <category><![CDATA[prebuilt-ai]]></category>
            <dc:creator><![CDATA[Gosia]]></dc:creator>
            <pubDate>Tue, 11 Apr 2023 20:28:03 GMT</pubDate>
            <atom:updated>2023-04-11T20:28:53.915Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="Get Started With Cognitive Services" src="https://cdn-images-1.medium.com/max/1024/1*PUuuYK50wQvAxZa-mQn5fA.png" /></figure><h3>What are Cognitive Services?</h3><p>Cognitive services are pre-built AI APIs for applications, programming languages and platforms. They are based on Deep Learning Research (Microsoft does all data preparation) and can easily help develop an intelligent application without machine learning knowledge.</p><p>In other words — they are Algorithms as a Service implemented via APIs into your application.</p><h3>Why Azure Cognitive Services?</h3><p>Azure Cognitive Services are easy to use and require only a few lines of code in your application to get quick results. There are also flexible — you can use your preferred programming language, such as C#, Python, Java, JavaScript, and Go. And the last — Cognitive Services are tested and built by experts from Microsoft Research, provided with quality documentation, sample code, and community support.</p><h3>Cognitive Services APIs</h3><p>Several categories will be changed/updated since this post comes to life. This list could be incomplete soon; you can find the full list of actual services on the <a href="https://azure.microsoft.com/en-gb/products/cognitive-services/">Azure Cognitive Services website</a>.</p><p>But for now (April 2023), there are five groups of Cognitive Services (some still on preview — that means you can play with them and create a proof of concept, but it is not recommended to implement those APIs on production as they could disappear for further research)</p><p>Here you can find a list of those services with a summary of what they can do for you:</p><h3>Vision APIs</h3><h3><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/">Computer Vision</a></h3><h4>OCR</h4><ul><li>OCR (Optical Character Recognition) –<em>text recognition</em> or <em>text extraction</em>.</li><li>Allows to extract text from images (printed or handwritten)</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/602/0*2Q3nzHfLxFOo8yvc.png" /></figure><h4>Image Analysis</h4><ul><li>Image tagging</li><li>Image categorisation</li><li>Category taxonomy</li><li>Image descriptions</li><li>Object detection</li><li>Brand detection</li><li>Face detection</li><li>Image type detection</li><li>Domain-specific content</li><li>Colour scheme detection</li><li>Adult content detection</li><li>Smart-cropped thumbnails</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/602/0*fpUczmRnNvXWJRrg.png" /></figure><h4>Face</h4><p>Based on Responsible AI, many attributes that used to be implemented in Face API will be removed, such as emotion, age, gender, smile, makeup etc.</p><p>Access to more details Face API is available only for specific solutions that Microsoft approves.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/752/0*BE2PNZmHvbOODkLw.png" /></figure><h4>Spatial Analysis</h4><ul><li>Detect the presence and movements of people in the video.</li><li>Analyse social distancing</li><li>Count people entering the zone.</li><li>Face mask detection</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/752/0*PdjDolxQ40MZdcOi.png" /></figure><h3><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/">Custom Vision</a></h3><ul><li>Customisable image recognition</li><li>Custom site: <a href="https://www.customvision.ai/">https://www.customvision.ai/</a></li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/752/0*vAaUpMPKbfNFFFLL.png" /></figure><h3>Speech APIs</h3><h3><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/">Speech Services</a></h3><h4>Speech-to-text</h4><h4>Text-to-speech</h4><h4>Speech translation</h4><h4>Speaker Recognition</h4><h4>Custom keyword</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/903/0*bugvx9D2Gp2wmUvA.png" /></figure><h3>Language APIs</h3><h3><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/language-service/">Language Services</a></h3><ul><li>Extract information</li><li>Summarizer text-based content</li><li>Classify Text</li><li>Understand conversations.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/752/0*GOYHcF25UBl3fXKy.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/622/0*-hdVMHi5tf00loMD.png" /></figure><h3><a href="https://www.luis.ai/">Language Understanding</a></h3><ul><li>Contextual language understanding</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/752/0*if51m6lc4GQTvdLe.png" /></figure><h3><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/qnamaker/">Question Answering</a></h3><ul><li>QnA extraction from unstructured text</li><li>Knowledgebase creation from collections of Q&amp;As</li><li>Semantic marching for knowledge bases</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/647/0*9hZLX0vTw_nSfZQJ.png" /></figure><h3><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/translator/">Translator</a></h3><ul><li>Text Translation</li><li>Document translation</li><li>Custom translation</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/752/0*MiIU59zreVPGvsOM.png" /></figure><h3>Decision APIs</h3><h3>Anomaly Detector</h3><ul><li>Identify potential problems early on</li><li>detect anomalies as they occur in real-time throughout your data set as a batch.</li><li>Get additional information about your data and adjust anomaly detection boundaries.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/602/0*TAMBVbvpMgFm1cBB.png" /></figure><h3>Content Moderator</h3><ul><li>Detected potential offensive and unwanted images.</li><li>Filter possible profanity and undesirable text</li><li>Moderate adult and racy content in videos</li><li>Use the built-in review tool for the best result.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/602/0*zQ_TK525XyEjUQWy.png" /></figure><h3>Personalizer</h3><ul><li>Deliver rich, personalised experiences in your apps.</li><li>Deploy anywhere, from the cloud to the edge.</li><li>Understand and efficiently manage the reinforcement learning loop.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/752/0*GwR1VQ6Jdv6eMVBL.png" /></figure><h3>Azure OpenAI</h3><p>OpenAI models are collections of Generative AI models — models that can produce new content based on what is described in the input, such as language, code and images.</p><p>Azure OpenAI have selected services from the OpenAI platform that give an environment for using them on the enterprise scale. It utilised Azure’s infrastructure, including security, compliance and regional availability.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/903/0*DGcJO2Owj5Xx3I3-.png" /></figure><h3>GPT-3/GPT-4</h3><ul><li>Summarizing text</li><li>Classify text.</li><li>Generating names of phrases</li><li>Translation</li><li>Answering questions</li><li>Suggesting content</li></ul><h3>DALL-E</h3><ul><li>Image Generation</li><li>Editing an image</li><li>Image variation</li></ul><h3>Codex</h3><ul><li>Creating code suggestions</li></ul><h3>Embedded</h3><ul><li>A set of models that can understand and use embeddings</li></ul><h3>Other services</h3><ul><li><a href="https://azure.microsoft.com/en-us/products/form-recognizer">Form Recogniser</a></li><li>Extract text, key-value pairs, and tables from documents</li><li>Customised to your form, without manual labelling.</li><li>Deploy anywhere, from the cloud to the edge.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/752/0*IxHtaIWchb4HWyNx.png" /></figure><ul><li><a href="https://azure.microsoft.com/en-us/services/media-services/video-indexer/">Video Indexer</a></li><li>Face detection in video</li><li>Object, scene, and activity and keyframe extraction and analysis</li><li>Custom site: <a href="https://www.videoindexer.ai/">https://www.videoindexer.ai/</a></li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*0SpANMysH7yw6JEe.png" /></figure><h3>Cognitive Services Labs</h3><p>Microsoft is also working on new APIs that will be available in feature to the Cognitive Services family.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/602/0*Mt3AIMa6eVqyHp0B.png" /></figure><p>All of them you can find on the Microsoft Research Site, and there is an excellent opportunity to have a real impact on those APIs by giving feedback to Microsoft on this project will be helpful and how they should evolve.</p><h3><a href="https://www.microsoft.com/en-us/research/project/academic-knowledge/">Project Academic Knowledge</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/903/0*-kiVzH6tJrC8j32K.png" /></figure><p>Tap into the wealth of academic content in the Microsoft Academic Graph using the Academic Knowledge API.</p><h3><a href="https://www.microsoft.com/en-us/research/project/knowledge-exploration/">Project Knowledge Exploration</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*MotnZgy4fJjIEJsi.png" /></figure><p>Enable interactive search experiences over structured data via natural language inputs.</p><h3><a href="https://www.microsoft.com/en-us/research/project/conversation-learner/">Project Conversation Learner</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*BObP4oLqQD22ZSoI.png" /></figure><ul><li>Learn from interaction examples.</li><li>Reduce manual coding of dialogue control logic.</li></ul><h3><a href="https://www.microsoft.com/en-us/research/project/answer-search/">Project Answer Search</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/903/0*ypR0kTV-cfJSbBfQ.png" /></figure><ul><li>AI that understands user queries</li><li>Targeted and faster results</li><li>Relevant results from Bing’s industry-leading web index and knowledge graph</li></ul><h3><a href="https://www.microsoft.com/en-us/research/project/event-tracking/">Project Event Tracking</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/903/0*0rEtJQe4UpfbYo-U.png" /></figure><ul><li>Finding events associated with Wikipedia entities.</li><li>List of related events organised by time.</li><li>Help to characterise events happening in future.</li></ul><h3><a href="https://www.microsoft.com/en-us/research/project/url-preview/">Project URL Preview</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/903/0*KUNFJV2-cuu1FLM_.png" /></figure><ul><li>Quickly provides a URL’s page title, brief description, and the most relevant image.</li><li>Instantly enhance social scenarios, such as chat apps, to let users know what they have been sent and improve their URL-sharing experience.</li><li>Leverage Project URL Preview to Suppress inappropriate or adult content, block URLs on protected networks, and get users to the right content faster.</li></ul><h3><a href="https://www.microsoft.com/en-us/research/project/gesture/">Project Gesture</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/903/0*Ky1ycG2i55-NtELY.png" /></figure><p>Add custom hand gestures to your app.</p><p><a href="https://youtu.be/k38ygfiAqVg">https://youtu.be/k38ygfiAqVg</a></p><h3>Container Support</h3><p>Cognitive Services can also be used with containers.</p><p>The benefits of using containers with Cognitive Services:</p><ul><li>Control over data — allows where data are processed (it’s suitable for companies that cannot send data to the cloud)</li><li>Control over model updates</li><li>Portable architecture — the application can be created on Azure, on-premises and at the edge.</li><li>High throughput / Low latency — the endpoint is strictly used for billing; no customer data ever flows that way.</li></ul><h3>Services supported by containers.</h3><p>Vision</p><ul><li><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/computer-vision-how-to-install-containers">Read OCR</a></li><li><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/spatial-analysis-container">Spatial Analysis</a></li></ul><p>Language</p><ul><li><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to-install-containers?tabs=sentiment">Sentiment Analysis</a></li><li><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to-install-containers?tabs=keyphrase">Key phrase extraction</a></li><li><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to-install-containers?tabs=language">Text language detection</a></li><li><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to-install-containers?tabs=healthcare">Text Analytics for health</a></li><li><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/luis/luis-container-howto">LUIS</a></li><li><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/translator/containers/translator-how-to-install-container">Translator</a></li></ul><p>Speech</p><ul><li><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/speech-container-howto?tabs=stt">Speech to text</a></li><li><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/speech-container-howto?tabs=cstt">Custom Speech to text</a></li><li><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/speech-container-howto?tabs=ntts">Neural text to speech</a></li><li><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/speech-container-howto?tabs=lid">Speech-language identification</a></li></ul><p>Decision</p><ul><li><a href="https://learn.microsoft.com/en-us/azure/cognitive-services/anomaly-detector/anomaly-detector-container-howto">Anomaly Detector</a></li></ul><h3>How to start with Cognitive Services?</h3><h3>Start for Free</h3><p>If you don’t have an Azure account, you can sign in to get £150 credits for 30 days and 12 months to popular services + 25+ always free services.</p><p>Most Cognitive Services you can use for free for development (as those services have restrictions on the number of calls per second and number of transactions per month)</p><p><a href="https://azure.microsoft.com/en-us/free/cognitive-services/">https://azure.microsoft.com/en-us/free/cognitive-services/</a></p><h3>Azure</h3><p>There are two ways to have an endpoint/key for Cognitive Services: get a bunch of services under one endpoint/key or create a new resource for each service.</p><h3>Cognitive Services multi-service account</h3><p>Create Cognitive Services if you want to use multiple services in your application.</p><p>This one endpoint/key pair (multi-service) support:</p><ul><li>Decision</li><li>Content Moderator</li><li>Language</li><li>Language Understanding (LUIS)</li><li>Language</li><li>Translator</li><li>Speech</li><li>Speech-to-text</li><li>Text-to-Speech</li><li>Speech translation</li><li>Vision</li><li>Computer Vision</li><li>Custom Vision</li><li>Face</li><li>Form Recognizer</li><li>Metrics Advisory</li></ul><p>The Cognitive Services resource is available in price S0 (so, it’s not free) and not with all regions.</p><ol><li>Create Cognitive Services</li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/903/0*LBK7unV5brYsS3WR.png" /></figure><p>Select (Unique) Name, Subscription, Location (Region), Pricing tier (for now, it’s only S0), select Resource Group ) and accept terms (<a href="https://www.microsoft.com/en-gb/licensing/product-licensing/products?rtc=1">https://www.microsoft.com/en-gb/licensing/product-licensing/products?rtc=1</a> ).</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/903/0*pWMoewb_7wMKPB36.png" /></figure><p>And after a few seconds, you can enjoy your API.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/903/0*0aQrqJLpexB39FNq.png" /></figure><p>Now, you can grab your key and endpoint and test them in your application.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/768/0*Xv9LXtRWDwHbA9TE.png" /></figure><h3>Specific Cognitive Services</h3><p>The creation of specific Cognitive Services is almost the same.</p><p>You are going to choose the service you would like to use:</p><ul><li>Azure OpenAI account</li><li>Speech service</li><li>Language Service</li><li>Translator</li><li>Language understanding (classic)</li><li>QnA Maker (classic)</li><li>Computer Vision</li><li>Custom Vision</li><li>Face API</li><li>Anomaly Detector</li><li>Content Moderator</li><li>Personalizer</li><li>Health Insight</li></ul><p>The difference is that you can choose the F0 tier — a free, limited tier.</p><p>For example, Personalizer has a limit of 50K transactions per month):</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/276/0*EaBAagh09ue7pJqz.png" /></figure><h3>Test your API</h3><p>If you don’t have your application written yet, but you would like to test and see what kind of result will back, you can use APIs services: <a href="https://westcentralus.dev.cognitive.microsoft.com/docs/services/">https://westcentralus.dev.cognitive.microsoft.com/docs/services/</a></p><p>For example, Computer Vision V3, Describe Image <a href="https://westeurope.dev.cognitive.microsoft.com/docs/services/computer-vision-v3-ga/">https://westeurope.dev.cognitive.microsoft.com/docs/services/computer-vision-v3-ga/</a></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/903/0*lUGAvIFSZ9ti3fqs.png" /></figure><p>Tested image:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/602/0*aI9ZRgqnF6rYIs-K.jpg" /></figure><p>And results:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/903/0*Z6OCI4-jjz4kYwJg.png" /></figure><h3>Application examples</h3><h3><a href="https://github.com/features/copilot">GitHub Co-pilot</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/602/0*TYK6R3vD__H6boqq.png" /></figure><h3><a href="https://designer.microsoft.com/">Microsoft Designer</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/682/0*--cs6rk44pS7NEiP.png" /></figure><h3><a href="https://www.microsoft.com/en-us/ai/seeing-ai">Seeing AI App</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/451/0*ebv-9NjU8oNjIchp.jpg" /></figure><h3><a href="https://www.bing.com/visualsearch">Bing Visual Search</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/903/0*FFnN_S65SvKxi99g.png" /></figure><h3><a href="https://algoevaluation.azurewebsites.net/#/">Anomaly Detector Interactive Demo</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/903/0*rpmv113R0Gm8oNLT.png" /></figure><h3>Resources</h3><ul><li><a href="https://www.amazon.co.uk/Microsoft-AI-MVP-Book-practical-ebook/dp/B082P5MK8Y/ref=sr_1_1?dchild=1&amp;keywords=ai+mvp&amp;qid=1585851521&amp;sr=8-1">Microsoft AI MVP Book</a></li><li><a href="https://docs.microsoft.com/en-us/azure/cognitive-services/welcome">Microsoft Docs</a></li><li><a href="https://aischool.microsoft.com/en-us/home">AI School</a></li><li><a href="https://www.microsoft.com/en-us/ai/ai-platform">AI Platform</a></li><li><a href="https://www.microsoft.com/en-us/research/lab/microsoft-research-ai/">Microsoft AI Research</a></li></ul><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=4d55b734e082" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Project Birds]]></title>
            <link>https://medium.com/women-in-all-things-data/project-birds-4b4c8c95af02?source=rss-7adfacbbf591------2</link>
            <guid isPermaLink="false">https://medium.com/p/4b4c8c95af02</guid>
            <category><![CDATA[azure-ai]]></category>
            <category><![CDATA[cognitive-services]]></category>
            <category><![CDATA[computer-vision]]></category>
            <category><![CDATA[iot]]></category>
            <category><![CDATA[azure]]></category>
            <dc:creator><![CDATA[Gosia]]></dc:creator>
            <pubDate>Tue, 13 Jul 2021 09:33:41 GMT</pubDate>
            <atom:updated>2021-07-13T09:33:41.016Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*6WH9zctVxC1hx7DndgWHnQ.jpeg" /></figure><p>Last year we had a lovely spring starting in April. I was unlucky to be on furlough during this time and had a lot of free time. One morning, I was sitting in my garden enjoying the weather, morning coffee and birdsong. Unfortunately, this idyllic morning was surrounded by pigeons or as my Dad calls them ‘flying rats’.</p><p>Pigeons know they are not welcome in my garden. Whenever they see any movement or hear how I shout at them, they run away. However, if there was another bird, the bird isn’t scared of my movement nor my voice.</p><p>I don’t want to sit at the window all day and check when the pigeon enters my garden (even if I have a lot of free time). So in my mind, I decided to create a project called “Project Bird” (codename: I hate pigeons).</p><p>The idea was simple: When any pigeon enters the garden — noise is made or lights are shone.</p><p><strong>Project Setup</strong></p><p>I already had all the tools: Raspberry PI, Camera and Azure Account, to start preparing the basic prototype.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*xgJVzs8VXUgghAhEIdYs-Q.jpeg" /></figure><p>There were four main steps to create this project:</p><ol><li>Get ready with Raspberry PI and get some simple webcam output.</li><li>Save photo to Azure/OneDrive when there is movement in the garden.</li><li>Create Custom Vision API to analyse birds in my garden</li><li>Add some sensor to create voice/movement etc., when there are only pigeons in the garden.</li></ol><p>The first step was easy to prepare. I had my Raspberry PI and a USB camera. I installed Windows 10 IoT Core and wrote a simple project (in C#) to have output from the camera.</p><p>Next, I wrote the custom code using the OpenCV library to make a photo when movement was detected. I decided to store all of these images in Azure Storage — to send them to Custom Vision and analyse them easily.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*T3F7KfVyLw4WgpjgM5IHyg.jpeg" /></figure><p><strong>Image preparation</strong></p><p>Before I could even start to analyse photos, I needed to train my Custom Vision to distinguish which birds are not pigeons.</p><p>When it comes to the longest stage — to manually check each photo, tag them to identify the bird, pigeon or other creature (e.g. cat, squirrel or fox). Then train Custom Vision and test the model with photos that were not part of training.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/602/1*Jyqhx_VGZ4lpy5hjt2eMQg.png" /></figure><p><strong>Why Custom Vision?</strong></p><p>Azure Cognitive Services offer two Image analysis services — Computer Vision and Custom Vision.</p><p>With Computer Vision, I could still analyse the birds probably from the tags, and I was able to obtain information if this was a pigeon. However, Computer Vision was not enough for me, as I needed to have the correct information if the photo was a pigeon. Custom Vision gives me the tools to tag my photos and create a model based on them.</p><p><strong>Realtime analysis</strong></p><p>When the motion was detected, the camera takes a picture. The picture goes to Azure Storage. When a new item was added to Azure Storage — Microsoft Flow (now known as Power Automate) takes a photo, sends it to Custom Vision Model. Custom Vision analyses the photo and tags it with the bird name. The information is then with the tag and sent back to Raspberry Pi. If this was a pigeon — the light was switched on. After the next movement (when the pigeons go away), the picture is analysed and the light is switched off.</p><p><strong>Potential improvements</strong></p><p>There are few things that I would improve with this project:</p><ul><li>OS — I used Windows IoT Core, and the problem with OS is that you can have a USB Camera. In this situation, when you have a special camera for Raspberry PI that can detect motion at night, you are unable to use it.</li><li>Programming language — because I would like to change the OS on Raspberry PI to non-Windows, automatically, I’ll write some code in Python (even if you can write in .NET Core, Python has more libraries for Data Science that can be easily used)</li><li>Internet — each image is sent to Azure Storage, then analysed and sent back to Raspberry PI and takes some time. Ideally, in this instance, it is best to have the model on Raspberry PI and run it offline. Synchronisation and removing images from the local storage can be done once per hour.</li><li>Sensor — I will use a voice recording to scare the pigeons, as the lights are not so penetrating during the day.</li></ul><p><strong>What did I learn?</strong></p><p>This was my first Raspberry PI project. I learnt a lot about setting up the tiny machine and how powerful it is. I tried many libraries for .NET about motion detection, but not all of them work smoothly with Raspberry PI on Windows IoT Core. The Custom Vision and Azure are very powerful and easy to set up and in less than a few hours, I have a model ready with automation via Power Automate.</p><p>And finally — my feelings for pigeons have not changed at all!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=4b4c8c95af02" width="1" height="1" alt=""><hr><p><a href="https://medium.com/women-in-all-things-data/project-birds-4b4c8c95af02">Project Birds</a> was originally published in <a href="https://medium.com/women-in-all-things-data">Women in all things Data</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[What are Cognitive Services?]]></title>
            <link>https://medium.com/@gosiai/what-are-cognitive-services-61c7925c983b?source=rss-7adfacbbf591------2</link>
            <guid isPermaLink="false">https://medium.com/p/61c7925c983b</guid>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[azure]]></category>
            <category><![CDATA[azure-ai]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[cognitive-services]]></category>
            <dc:creator><![CDATA[Gosia]]></dc:creator>
            <pubDate>Fri, 26 Jun 2020 00:00:00 GMT</pubDate>
            <atom:updated>2020-06-26T10:56:15.506Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*yN0EqfDsZA1bEnCK72qmnQ.png" /></figure><p>Cognitive Services are pre-built AI APIs that you can use in any application, any programming language and any platform. They based on Deep Learning Research (Microsoft does all data preparation) and are easy to help to develop an intelligent application without any machine learning knowledge.</p><p>In other words — there are Algorithms as a Service implemented via APIs into your application.</p><p>Cognitive Services are part of Microsoft AI platform, and it uses Machine Learning and Deep Learning Algorithms.</p><h3>What exactly means those terms?</h3><h3>Artificial Intelligence (AI)</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/150/1*uUJr-3IBynSTELTStGAgQA.png" /></figure><p>The Artificial Intelligence term is not new, but it’s definition changes since the first use of it.</p><p>Alan Turing created the first paper about AI in 1950: “ <a href="https://www.csee.umbc.edu/courses/471/papers/turing.pdf">Computer Machinery and Intelligence</a>”, where he tried to answer the question <em>“Can machines think?”</em> — and based on that <strong>Turing Test</strong> term was well known as a method for determining if a machine is intelligent.</p><p>From that time, there was a lot of changes, where people played around the algorithms and writing different programs with intelligent behaviour, such as playing chess or automatic translation. New programming languages were developed to create more clever programs such as PROLOG (1972) — the first logic programming language or MATLAB (1984), software to accelerating engineers and science.</p><p>Based on <strong><em>Artificial Intelligence: A Modern Approach</em></strong> by <em>Stuart Russell</em> and <em>Peter Norvig</em>, there are four categories of Artificial Intelligence, such as:</p><p><strong><em>Systems that think like humans</em></strong></p><ul><li>“The exciting new effort to make computers think… machine with minds, in the full and literal sense.” (Haugeland, 1985)</li><li>“[The automation of] activities that we associate with human thinking, activities such as decision-making, problem solving, learning…” (Bellman, 1978)</li></ul><p><strong><em>Systems that think rationally</em></strong></p><ul><li>“The study of mental faculties through the use of computational models.” (Charniak and McDernott, 1985)</li><li>“The study of the computations that make it possible to perceive, reason and act.” (Winston, 1992)</li></ul><p><strong><em>Systems that act like human</em></strong></p><ul><li>“The act of creating machines that perform functions that require intelligence when performed by people” (Kurzweil, 1990)</li><li>“The study of how to make computers do things at which, at the moment, people are better” (Rich and Knight, 1991)</li></ul><p><strong><em>Systems that act rationally</em></strong></p><ul><li>“Computational Intelligence is the study of the design of intelligent agents” (Poole et al., 1998)</li><li>“AI… is concerned with intelligent behaviour in artefacts” (Nilsson, 1998)</li></ul><p>Artificial Intelligence is a system that can learn from data and based on that, decide to achieve a specific goal or task using Machine Learning. Natural Language Processing, Speech, Vision, Robotics etc.</p><p>AI is an entire field dedicated to making machines smart. AI is an umbrella for all intelligent algorithms.</p><h3>Machine Learning (ML)</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/150/1*RtirJIcVGvyv6uT8WTvHyQ.png" /></figure><p>Machine Learning is a division of Artificial Intelligence. ML analyses, understand and identify a pattern in the data, such as recognise text, recognise voice etc.</p><p>There are two main types of Machine Learning:</p><ul><li>Supervised Learning — getting dataset with labelled training data and training examples — it’s based on input-output pairs</li><li>Unsupervised Learning — predict outcomes on the recognising patterns in input data.</li></ul><h3>Deep Learning (DP)</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/150/1*UV8f9slDnZ5bG6bOt0uXvw.png" /></figure><p>Deep Learning is a subset of Machine Learning and Artificial Intelligence. It’s using Artificial Neural Networks that was created based on biological neural networks in human. It’s using multiple layers to extract higher-level features from the raw input progressively.</p><h3>In other words</h3><p>Artificial Intelligence, Machine Learning and Deep Learning are techniques to help you create an intelligent program.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/495/1*BE5ljsomMW_wR2aWMctIfg.png" /></figure><h3>Do you need to know all of these fields in details?</h3><p>The quick answer is no. You don’t need to know Machine Learning or Deep Learning Algorithms to use AI in your program. It’s nice to know the basics about Artificial Intelligence. Still, big companies like Microsoft, Google, AWS or IBM created a bunch of APIs that you can use in your application to give them some kind of intelligence. All of these APIs are trained models that were developed based on a large amount of data, prepared by data scientists. And this what you need to do — just add them to your application.</p><h3>Why Microsoft Cognitive Services?</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/150/1*FzxECTIwVd3FXV2QMf_1pA.png" /></figure><p>Microsoft Cognitive Services are pre-built AI API’s. There are <strong>easy</strong> to use and requires only a few lines of code in your application to get quick results. There are as well <strong>flexible</strong> — you can use your own, preferred programming language, such as C#, Python, Java, JavaScript, Go. And the last — Cognitive Services are <strong>tested</strong> and built by experts from Microsoft Research, provided with quality documentation, sample code and as well as community support.</p><h3>Cognitive Services APIs</h3><p>Several categories will be changed/updated since this post will come to life. So this list could be incomplete soon and the full list of actual services you can find on Azure Cognitive Services website.</p><p>But for now (June 2020) there are five groups of Cognitive Services (some still on preview — that means you can play with them, create a proof of concept, but it’s not recommended to implement those APIs on production as they could disappear for further research)</p><p>Here you can find a list of those services with a summary of what they can do for you:</p><h3>Vision APIs</h3><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/computer-vision/#features">Computer Vision</a></h3><ul><li>Image classification</li><li>Scene and activity recognition in images</li><li>Celebrity and landmark recognition in images</li><li>Optical character recognition (OCR) in images</li><li>Handwriting recognition</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*2K7xeQ7RE8DNLfpFpKRfsg.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/ink-recognizer/">Ink Recognizer (Preview)</a></h3><ul><li>Recognise digital ink and handwriting</li><li>Recognise and pinpoint common shapes</li><li>Enable productivity scenarios</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*tKtboNoqBNK3kigUjGyljg.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/custom-vision-service/">Custom Vision</a></h3><ul><li>Customisable image recognition</li><li>Custom site: <a href="https://www.customvision.ai/">CustomVision.ai</a></li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*8FW_u_XY-S3ESOPhhl-O8A.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/face/">Face</a></h3><ul><li>Face detection in images</li><li>Person identification in images</li><li>Emotion recognition in images</li><li>Similar face recognition and grouping in images</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*EhWfCRweEOsRt23Af-EG9A.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/media-services/video-indexer/">Video Indexer</a></h3><ul><li>Face detection in video</li><li>Object, scene, and activity and keyframe extraction and analysis</li><li>Custom site: <a href="https://www.videoindexer.ai/">https://www.videoindexer.ai/</a></li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*X_jYR4FJr1pLdySQZGaAQQ.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/form-recognizer/">Form Recognizer (Preview)</a></h3><ul><li>Extract text, key-value pairs, and tables from documents</li><li>Customised to your form, without manual labelling</li><li>Deploy anywhere, from the cloud to the edge</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Y5_EhIRuX7kpwU3q-yb2ZA.png" /></figure><h3>Speech APIs</h3><h3>Speech Services (<a href="https://azure.microsoft.com/en-us/services/cognitive-services/speech-to-text/">Speech to Text</a>, <a href="https://azure.microsoft.com/en-us/services/cognitive-services/text-to-speech/">Text to Speech</a>, <a href="https://azure.microsoft.com/en-us/services/cognitive-services/speech-translation/">Speech Translation</a>)</h3><ul><li>Automatic speech-to-text transcription with customisable models</li><li>Natural text-to-speech with custom voice fonts</li><li>Real-time speech translation</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*cgQB3vBj1UJc02rF8lgr6g.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/speaker-recognition/">Speaker Recognition (Preview)</a></h3><ul><li>Speaker identification</li><li>Speaker verification</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*MNn2rzMqC5Qu8zNQVHLJ5Q.png" /></figure><h3>Language APIs</h3><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/text-analytics/">Text Analytics</a></h3><ul><li>Named Entity Recognition</li><li>Key phrase extraction</li><li>Text sentimental analysis</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*jbdLgHudY2fUpSCtub575A.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/immersive-reader/">Immersive Reader (Preview)</a></h3><ul><li>Support readers of all abilities</li><li>Translated to 60+ languages</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*A1J7anPW6VfP9244YfjxpQ.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/translator">Translator</a></h3><ul><li>Automatic language detection</li><li>Automated text translation</li><li>Customisable translation</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*-BifobPz-PG1n8ov-nEwTA.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/qna-maker/">QnA Maker</a></h3><ul><li>QnA extraction from unstructured text</li><li>Knowledgebase creation from collections of Q&amp;As</li><li>Semantic marching for knowledge bases</li><li>Custom site: <a href="https://www.qnamaker.ai/">https://www.qnamaker.ai/</a></li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*AUIDY8Umv0lNfhKYWEZqXw.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/language-understanding-intelligent-service/">Language Understanding</a></h3><ul><li>Contextual language understanding</li><li>Custom site: <a href="https://www.luis.ai/">https://www.luis.ai/</a></li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ZTW908P06hbzJXYpC-kQ_A.png" /></figure><h3>Web Search</h3><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/bing-web-search-api/">Bing Web Search</a></h3><ul><li>Ad-free web search</li><li>Safe web search</li><li>Location-aware web search</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*KwcSQS1dUrBIo2CHq0XN6g.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/bing-custom-search/">Bing Custom Search</a></h3><ul><li>Custom search engine creation</li><li>Ad-free custom search results</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*F_oDtdQHguVrBSG8yMdLmg.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/bing-video-search-api/">Bing Video Search</a></h3><ul><li>Ad-free video search</li><li>Video topic and trend identification</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*E9qg222A0WV7XmTk9p_4lA.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/bing-image-search-api/">Bing Image Search</a></h3><ul><li>Ad-free image search</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*nuncL-uGeoKaLopS4aZ9ag.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/bing-visual-search/">Bing Visual Search</a></h3><ul><li>Identification of similar images and products</li><li>Knowledge acquisition from images</li><li>Web source identification</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*eXhttOP5OeqTJV7o_PD_zQ.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/bing-entity-search-api/">Bing Entity Search</a></h3><ul><li>Named entity recognition and classification</li><li>Knowledge acquisition for named entities</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*68kOkYfMloctc4kb50GJew.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/bing-news-search-api/">Bing News Search</a></h3><ul><li>Ad-free news search results</li><li>Trending topic identification</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*k6vkaHMVBsAQDxTKTlC1xQ.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/autosuggest/">Bing Autosuggest</a></h3><ul><li>Search query autocomplete</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ab0eFtSqblXgGKOBc6VdrA.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/spell-check/">Bing Spell Check</a></h3><ul><li>Web-scale, multi-lingual spell checking</li><li>Contextual spell checking</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*V1q2MrVTzN3wnz22YI3Dqg.png" /></figure><h3>Decision APIs</h3><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/anomaly-detector/">Anomaly Detector (Preview)</a></h3><ul><li>Identify potential problems early on</li><li>Detect anomalies as they occur in real-time, throughout your data set as a batch.</li><li>Get additional information about your data and adjust anomaly detection boundaries.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/1*dfHWH14k8hrygOi0w7O7PA.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/content-moderator/">Content Moderator</a></h3><p>*Detected potential offensive and unwanted images</p><ul><li>Filter possible profanity and undesirable text</li><li>Moderate adult and racy content in videos</li><li>Use built-in review tool for best result</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/1*lyVs8Mt6tzR5jq1Mc1VT5g.png" /></figure><h3><a href="https://azure.microsoft.com/en-us/services/cognitive-services/personalizer/">Presonalizer</a></h3><ul><li>Create a rich, personalised experience for every user.</li><li>Deliver rich, personalised experiences in your apps</li><li>Deploy anywhere, from the cloud to the edge</li><li>Understand and efficiently manage the reinforcement learning loop</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Bhg3POCRoY3bKA8eEImvWA.png" /></figure><h3>Cognitive Services Labs</h3><p>Microsoft is also working on new APIs that probably will be available in feature to Cognitive Services family.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*XiXwViP3Nv6T57S7UAtjZA.png" /></figure><p>All of them could you can find on <a href="https://www.microsoft.com/en-us/research/group/cognitive-research/">Microsoft Research Site</a>, and there is an excellent opportunity to have a real impact into those APIs by giving feedback to Microsoft with of this project will be helpful and how they should evolve.</p><h3><a href="https://www.microsoft.com/en-us/research/project/academic-knowledge/">Project Academic Knowledge</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/847/1*JXiQvSP9bEEQ72pYfIpaJQ.png" /></figure><ul><li>Uses <a href="https://www.microsoft.com/en-us/research/project/microsoft-academic-graph/?from=http%3A%2F%2Fresearch.microsoft.com%2Fmag">Microsoft Academic Graph</a></li><li>Getting access to academic knowledge</li></ul><h3><a href="https://www.microsoft.com/en-us/research/project/knowledge-exploration/">Project Knowledge Exploration</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*QVs6o-gNeYI7Ob57SnwBOQ.png" /></figure><ul><li>Interactive search experience for academic publication</li><li>Contains 1000 academic papers published by Microsoft Research</li></ul><h3><a href="https://www.microsoft.com/en-us/research/project/conversation-learner/">Project Conversation Learner</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*whuUJdGtLrVt1925LWjxZA.png" /></figure><ul><li>Learn from interaction examples</li><li>Reduce manual coding of dialogue control logic</li></ul><h3><a href="https://www.microsoft.com/en-us/research/project/personality-chat/">Project Personality Chat</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*mOk8dxDdAHEzG5qdQcL3Sw.png" /></figure><ul><li>Small talk with a bot</li><li>Personality to choose: Profesional, Enthusiastic, Caring, Witty, Friendly</li><li>Nearly 100 chit-chats scenarios for each personality</li><li>Can be added during create a QnA bot (QnA Maker)</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*dyl3bpj9Gt_DIObatRD7ug.png" /></figure><h3><a href="https://www.microsoft.com/en-us/research/project/answer-search/">Project Answer Search</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*4L23rhzz5J8WgEToJoTz1Q.png" /></figure><ul><li>AI that understand user queries</li><li>Targeted and faster results</li><li>Relevant results from Bing’s industry-leading web index and knowledge graph</li></ul><h3><a href="https://www.microsoft.com/en-us/research/project/event-tracking/">Project Event Tracking</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*RZ56BkZv4p_MaxFjLiG6xg.png" /></figure><ul><li>Finding events associated with Wikipedia entities</li><li>List of related events organised by time</li><li>Help to characterise events happening in future</li></ul><h3><a href="https://www.microsoft.com/en-us/research/project/url-preview/">Project URL Preview</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*M-iFILJa2sgi0fuqIzLorw.png" /></figure><ul><li>Quickly provides a URL’s page title, brief description, and the most relevant image</li><li>Instantly enhance any social scenarios such as chat apps to let users know what they have been sent and improve their URL sharing experience.</li><li>Leverage Project URL Preview to Suppress inappropriate or adult content, block URLs on protected networks, and get users to the right content faster.</li></ul><h3><a href="https://www.microsoft.com/en-us/research/project/gesture/">Project Gesture</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*weFVvCYLJFaXyodnL_z-Bw.png" /></figure><ul><li>Add custom hand gesture to your app</li></ul><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fwww.youtube.com%2Fembed%2Fk38ygfiAqVg%3Ffeature%3Doembed&amp;display_name=YouTube&amp;url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3Dk38ygfiAqVg&amp;image=https%3A%2F%2Fi.ytimg.com%2Fvi%2Fk38ygfiAqVg%2Fhqdefault.jpg&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=youtube" width="854" height="480" frameborder="0" scrolling="no"><a href="https://medium.com/media/789863a7b5569d1661c2f2a5fe3cd8c3/href">https://medium.com/media/789863a7b5569d1661c2f2a5fe3cd8c3/href</a></iframe><h3><a href="https://www.microsoft.com/en-us/research/project/anomaly-finder/">Project Anomaly Finder</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*FmkgsHc6ryWOuI0QQlG6hw.png" /></figure><ul><li>Monitoring data over time and detecting anomalies</li><li>It’s now part of <a href="https://azure.microsoft.com/en-us/services/cognitive-services/anomaly-detector/">Anomaly Detector (preview)</a></li></ul><h3><a href="https://www.microsoft.com/en-us/research/project/custom-decision/">Project Custom Decision</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*HAl4COB_PzR9aQz_82UxaA.png" /></figure><ul><li>Understand the context from the information user provide</li><li>Ranks the options and makes a decision</li><li>Automatically optimises based on user feedback</li></ul><h3><a href="https://www.microsoft.com/en-us/research/project/local-insights/">Project Local Insights</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*NOmPKdJS5sCwcSRllJMqcg.png" /></figure><ul><li>Provides insight into business and entities within a given area that can be reached by driving, walking or public transit within a given time or distance</li><li>It’s now part of <a href="https://docs.microsoft.com/en-us/bingmaps/rest-services/routes/local-insights">Bing Map Local Insights API</a></li></ul><h3><a href="https://www.microsoft.com/en-us/research/project/ink-analysis/">Project Ink Analysis</a></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*QyjVe1J63EU3gtX2f64iDg.png" /></figure><ul><li>Understanding digital ink content</li><li>Understanding: Words written by user, Structure of content, Shapes</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Dbf2-UNb4vn-zV4wtu5djQ.png" /></figure><h3>Container support</h3><p>Cognitive Services can also be used with containers.</p><p>The benefits of using containers with Cognitive Services:</p><ul><li>Control over data — allows where data are processing (it’s suitable for companies that cannot send data to the cloud)</li><li>Control over model updates</li><li>Portable architecture — the application can be created on Azure, on-premises and at the edge</li><li>High throughput / Low latency — the endpoint is strictly used for billing only, no customer data ever flows that way</li></ul><h3>Services supported by containers</h3><ul><li><a href="https://docs.microsoft.com/en-us/azure/cognitive-services/anomaly-detector/anomaly-detector-container-howto">Anomaly Detector</a></li><li><a href="https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/computer-vision-how-to-install-containers">Computer Vision</a></li><li><a href="https://docs.microsoft.com/en-us/azure/cognitive-services/face/face-how-to-install-containers">Face</a></li><li><a href="https://docs.microsoft.com/en-us/azure/cognitive-services/form-recognizer/form-recognizer-container-howto">Form Recogniser</a></li><li><a href="https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-container-howto">Language Understanding (LUIS)</a></li><li><a href="https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/speech-container-howto">Speech Service API</a></li><li><a href="https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to-install-containers">Text Analytics</a></li></ul><h3>How to start with Cognitive Services</h3><h3>Try Cognitive Services</h3><p>You can try Cognitive Services for free (without Azure account).</p><p>Go to site: <a href="https://azure.microsoft.com/en-us/try/cognitive-services/my-apis/">https://azure.microsoft.com/en-us/try/cognitive-services/my-apis/</a> and signup/login with your email.</p><p>For seven days, you will be able to test API’s. You will get endpoints and keys that couldn’t be changed:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*gdzmMGIMNCdDpP-EyYx0UA.png" /></figure><p>You will have access to services:</p><ul><li>Computer Vision</li><li>Face</li><li>Speech services</li><li>Speaker Recognition</li><li>Bing Spell Check API v7</li><li>Bing Search APIs v7</li><li>Text Analytics</li><li>Bing Autosuggest API v7</li><li>Bing Custom Search</li><li>Bing Entity Search</li><li>Ink Recognizer</li><li>Anomaly Detector</li><li>Personalizer</li></ul><h3><a href="https://azure.microsoft.com/en-us/free/cognitive-services/">Start for free</a></h3><p>If you don’t have Azure account you can sign in to get £150 credit for 30 days, 12 months to popular services + 25+ always free services: you can sign-in here: <a href="https://azure.microsoft.com/en-us/free/cognitive-services/">Azure Free Account</a>.</p><p>Most of Cognitive Services you can use for free for development (as those services have restriction of the number of calls per second and number of transaction per month)</p><h3>Azure</h3><p>There are two ways to have an endpoint/key for Cognitive Services: get a bunch of services under one endpoint/key or create a new resource for each service.</p><h3>Cognitive Services</h3><p>Create Cognitive Services if you want to use more than one service in your application.</p><p>This one endpoint/key pair (multi-service) support:</p><ul><li>Computer Vision</li><li>Face</li><li>Content Moderator</li><li>Language Understanding (LUIS)</li><li>Translator</li><li>Text Analytics</li><li>Bing Search v7 (Web, Image, News, Video, Visual)</li><li>Bing Custom Search</li><li>Bing Entity Search</li><li>Bing Autosuggest</li><li>Bing Spell Check</li></ul><p>The Cognitive Services resource is available in price S0 (so, it’s not a free resource) and not with all regions.</p><p>Create Cognitive Services</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*q5baoRw3Cid2u0zsPtWGMg.png" /></figure><p>Select (Unique) Name, Subscription, Location (Region), Pricing tier (for now it’s only S0), select Resource Group ) and accept <a href="https://www.microsoft.com/en-gb/licensing/product-licensing/products?rtc=1">terms</a>.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*mrVSBmNty216g9sxKa4r4g.png" /></figure><p>And after a few seconds, you can enjoy your API</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*YpzlUSrOdugDu9vl6h03bA.png" /></figure><p>Now, you can grab your key and endpoint and test them in your application.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/768/1*pqW8f5wDPXdW9Fwm48R87g.png" /></figure><h3>Specific Cognitive Services</h3><p>The creation of specific Cognitive Services is almost the same. You going to choose the service you would like to use:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*LCNS4XeLOwyFPZ9S0mzgkQ.png" /></figure><p>The difference here is that you can choose F0 tier — free, limited tier. For example, Personalizer has a limit to 50K transactions per month):</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/276/1*Or7pA--GUwc6gdarmQdhhA.png" /></figure><h3>Test your API</h3><p>If you don’t have your application written yet, but you would like to test and see what kind of result will back, you can use APIs services: <a href="https://westcentralus.dev.cognitive.microsoft.com/docs/services/">https://westcentralus.dev.cognitive.microsoft.com/docs/services/</a></p><p>For example: Computer Vision V3, Describe Image <a href="https://westeurope.dev.cognitive.microsoft.com/docs/services/computer-vision-v3-ga/">https://westeurope.dev.cognitive.microsoft.com/docs/services/computer-vision-v3-ga/</a></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*N5AE62L-7dmk_AQCj7afZg.png" /></figure><p>Tested image:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*0MJ8oXEddvHjylzi.jpg" /></figure><p>And result:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/964/1*Ik9XJ4pxdyEqkN1dm3pJ0g.png" /></figure><h3>Application examples</h3><ul><li><a href="https://github.com/microsoft/Cognitive-Samples-IntelligentKiosk">Intelligent Kiosk</a></li><li><a href="https://www.microsoft.com/en-us/ai/seeing-ai">Seeing AI App</a></li><li><a href="https://www.microsoft.com/en-us/translator/help/presentation-translator/">PowerPoint Presentation Translator</a></li><li><a href="https://www.bing.com/visualsearch">Bing Visual Search</a></li><li><a href="https://algoevaluation.azurewebsites.net/#/">Anomaly Detector Interactive Demo</a></li></ul><h3>Resources</h3><ul><li><a href="https://www.amazon.co.uk/Microsoft-AI-MVP-Book-practical-ebook/dp/B082P5MK8Y/ref=sr_1_1?dchild=1&amp;keywords=ai+mvp&amp;qid=1585851521&amp;sr=8-1">Microsoft AI MVP Book</a></li><li><a href="https://docs.microsoft.com/en-us/azure/cognitive-services/welcome">Microsoft Docs</a></li><li><a href="https://aischool.microsoft.com/en-us/home">AI School</a></li><li><a href="https://www.microsoft.com/en-us/ai/ai-platform">AI Platform</a></li><li><a href="https://www.microsoft.com/en-us/research/lab/microsoft-research-ai/">Microsoft AI Research</a></li></ul><h3>References</h3><ul><li><em>Haugeland, J. (1985).</em> <strong><em>Artificial Intelligence: The Very Idea</em></strong>. Cambridge, Massachusetts: Bradford.</li><li><em>Bellman, R. (1978).</em> <strong><em>An introduction to artificial intelligence: Can computers think?.</em></strong> Thomson Course Technology</li><li><em>Charniak, E.A. and McDermott, D.V. (1985)</em> <strong><em>Introduction to Artificial Intelligence.</em></strong> Addison-Wesley Pub.Company</li><li><em>Kurzweil, R. (1990)</em>. <strong><em>The Age of Intelligent Machines.</em></strong> MIT Press, Cambridge, Massachusetts.</li><li><em>Rich, E. and Knight, K. (1991)</em>. <strong><em>Artificial Intelligence</em></strong>, McGraw Hill, New York.</li><li><em>Poole, D. L., Mackworth, A. K., &amp; Goebel, R. (1998)</em>. <strong><em>Computational intelligence: a logical approach (Vol. 1).</em></strong> New York: Oxford University Press.</li><li><em>Nilsson, N. J. (1998).</em> <strong><em>Artificial intelligence: A new synthesis.</em></strong> San Francisco, CA: Morgan Kaufmann</li><li><em>Russell, S., Norivig, P. (2003)</em>, <strong><em>Artificial Intelligence. A Modern Approach. International Edition.</em></strong> Pearson Education Inc., New Jersey</li></ul><p><em>Originally published at </em><a href="https://gosiaborzecka.net/2020/06/what-are-cs/"><em>https://gosiaborzecka.net</em></a><em> on June 26, 2020.</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=61c7925c983b" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Project Birds (Phase 1)]]></title>
            <link>https://medium.com/@gosiai/project-birds-phase-1-1533db9a0296?source=rss-7adfacbbf591------2</link>
            <guid isPermaLink="false">https://medium.com/p/1533db9a0296</guid>
            <category><![CDATA[windows-10-iot-core]]></category>
            <category><![CDATA[raspberry-pi]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[analysis]]></category>
            <category><![CDATA[cognitive-services]]></category>
            <dc:creator><![CDATA[Gosia]]></dc:creator>
            <pubDate>Wed, 06 May 2020 00:00:00 GMT</pubDate>
            <atom:updated>2020-05-06T12:27:44.210Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*QVOuSWIv0d4aBybZ.jpg" /></figure><h3>The project bird idea</h3><p>To my garden time to times come some birds. They are nice, sing nice and they all are welcome but one — the pigeons. I simply don’t like them and don’t want that they walk around my garden.<br>So, I wanted to create something that will show them and only them that they should go. And this what all birds don’t like is some movement or loud voice or even clapping. And with this come the idea to get my old Raspberry PI and finally use it.</p><p>There are a few phases of the project:</p><ol><li><a href="https://gosiaborzecka.net/2020/05/ProjectBirdPhase1/">Get ready with Raspberry PI and get some simple webcam output</a></li><li>Save photo to Azure/OneDrive when some motion will happen on the garden</li><li>Create Custom Vision API to analyse with birds I like</li><li>Add some sensor to create voice/movement etc when only pigeons are in the garden</li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*3TQZXu3c6cjsH38S.jpg" /></figure><p>The first phase was to get ready my Raspberry PI with webcam:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*UffMGFMcyEWE1cic.jpg" /></figure><p>For this project, I use Raspberry PI 2 Model B and old Microsoft webcam ideal for this prototype.</p><h3>IoT Dashboard</h3><p>I installed the <a href="https://docs.microsoft.com/en-us/windows/iot-core/downloads">IoT Dashboard</a> to set up my device with Windows IoT Core. To do that I’ve added Device name, OS Build, Device name and administrator password and inserted my microSD card to install Windows 10 IoT Core on this card.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*BulkUlRzUM9Yabs0.png" /></figure><p>After a few minutes, the download and installation on the SD card were completed and I could put the microSD card into my Raspberry PI.</p><p>A few minutes and restarts later, the Raspberry PI was</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*erecSAJEYs8I7qdQ.jpg" /></figure><p>And when I’ve checked that my laptop is on the same domain as Raspberry PI, I started to see my device on the IoT Dashboard:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*rG0k2tRjM1L2d_yv.png" /></figure><p>My device was ready to start developing!</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*AAJgVKeTifdrx6Vh.png" /></figure><h3>Development time!</h3><p>First, I read how I can start to develop application and I found that one way is to use <strong>Universal Windows Platform</strong> development that I’m not used at all before. So I back to Visual Studio Installer and added missing component.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*7LSSppbFC1vbqmdq.png" /></figure><h3>Created a blank app</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*WKfZYRZdBttQraRo.png" /></figure><p>and the target for Windows 10 (as my Raspberry Pi already have Windows 10 IoT)</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*ba-q4rkJ6LBNJ7YN.png" /></figure><h3>Debug code on Raspberry PI</h3><p>To be sure that everything I setup correctly, I started by creating a simple project to debug it in the device.</p><p>I used grids to have three things: • Photo (Video) • Logs • Current date and time</p><p>The code I use was for MainPage.xaml</p><pre>&lt;Grid&gt;<br>    &lt;Grid.RowDefinitions&gt;<br>        &lt;RowDefinition/&gt;<br>        &lt;RowDefinition/&gt;<br>    &lt;/Grid.RowDefinitions&gt;<br>    &lt;Grid.ColumnDefinitions&gt;<br>        &lt;ColumnDefinition /&gt;<br>        &lt;ColumnDefinition /&gt;<br>    &lt;/Grid.ColumnDefinitions&gt;</pre><pre>    &lt;Image Height=&quot;480&quot; Width=&quot;730&quot; HorizontalAlignment=&quot;Center&quot; VerticalAlignment=&quot;Center&quot; Stretch=&quot;Fill&quot; Source=&quot;https://i.ytimg.com/vi/yJRarYStGEM/maxresdefault.jpg&quot; /&gt;<br>    &lt;TextBlock x:Name=&quot;txtinformation&quot; Grid.Column=&quot;1&quot; Grid.ColumnSpan=&quot;2&quot; Grid.Row=&quot;0&quot; Text=&quot;I see something...&quot; HorizontalAlignment=&quot;Center&quot; VerticalAlignment=&quot;Center&quot; FontSize=&quot;50px&quot; Foreground=&quot;GreenYellow&quot; /&gt;<br>    &lt;TextBlock x:Name=&quot;txtdatetime&quot; Grid.Column=&quot;0&quot; Grid.Row=&quot;1&quot; Text=&quot;Time&quot; HorizontalAlignment=&quot;Center&quot; VerticalAlignment=&quot;Center&quot; FontSize=&quot;50px&quot; Foreground=&quot;DeepSkyBlue&quot; /&gt;<br>&lt;/Grid&gt;</pre><p>And MainPage.xaml.csadded simple current datetime</p><pre>txtdatetime.Text = DateTime.Now.ToString();</pre><p>First I tested on the local machine that everything is working correctly.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*-bDXwcBpTXBrDird.png" /></figure><p>And next try to debug on the device. To do that I selected the Remote Machine</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*PyIgedJiBhKRjQZD.png" /></figure><p>Find my device with Universal authentication mode</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*sysOPvbVJIGIIQ_A.png" /></figure><p>And got an error.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*24HqFVQUg7g-_oEq.png" /></figure><p>For me, the error is shown because I was not set up to use ARM version</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*7jJPrXeCBujNHrtr.png" /></figure><p>When resolving this issue, clean and rebuild the project I could happily see that from now I can debug my code on the Raspberry Pi.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*vq52QQkZiH5bugTE.jpg" /></figure><h3>Adding webcam output</h3><p>Now, I want to replace picture with output from the camera.</p><p>To do that I used a build-in canvas and change the Image code with:</p><p>MainPage.xaml</p><pre>&lt;Canvas Name=&quot;PreviewCanvas&quot; Grid.Row=&quot;0&quot; Grid.Column=&quot;0&quot; Background=&quot;Gray&quot; Visibility=&quot;Visible&quot;&gt;<br>    &lt;CaptureElement x:Name=&quot;previewElement&quot; Visibility=&quot;Visible&quot; HorizontalAlignment=&quot;Center&quot; VerticalAlignment=&quot;Center&quot; Stretch=&quot;Fill&quot; RequestedTheme=&quot;Light&quot;&gt;&lt;/CaptureElement&gt;<br>&lt;/Canvas&gt;</pre><p>MainPage.xaml.cs</p><pre>public async void InitMediaCapture()<br>{<br>    try<br>    {<br>        MediaCapture = new MediaCapture();<br>        await mediaCapture.InitializeAsync();<br>        previewElement.Source = mediaCapture;<br>        await mediaCapture.StartPreviewAsync();<br>    }<br>    catch(Exception ex)<br>    {<br>        throw;<br>    }<br>}</pre><p>When I run my code, I’ve got an error message: There are no more endpoints available from the endpoint mapper</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*MlbAgS_ir2N9jvGx.png" /></figure><p>On the local machine, where the camera is build-in, the error was little different: “Access is Denied”</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/436/0*_tBdDD4XYerkzxAj.png" /></figure><p>It takes me a while to find that the changes need to be added into an app manifest:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/395/0*oqZ81WmVqsq6huGx.png" /></figure><p>The checkbox that I needed to add to see changes was: • Webcam • Microphone</p><p>On the local machine, it asked me to allow use the microphone and webcam and on Raspberry PI it’s just started working nice.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/500/0*N1fqFQKkAkOVXPJe.jpg" /></figure><p>And I think birds already knew that I’m doing a project about birds because the thousands of them come to visit my garden 😊</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/480/0*D1fq3esY61v9Gsy6.gif" /></figure><p><em>Originally published at </em><a href="https://gosiaborzecka.net/2020/05/ProjectBirdPhase1/"><em>https://gosiaborzecka.net</em></a><em> on May 6, 2020.</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=1533db9a0296" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>