<?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 Karimkhan on Medium]]></title>
        <description><![CDATA[Stories by Karimkhan on Medium]]></description>
        <link>https://medium.com/@karimkhan.it?source=rss-94455fbaa618------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*FYffaI8V0J1T5OcT4kdc_A.jpeg</url>
            <title>Stories by Karimkhan on Medium</title>
            <link>https://medium.com/@karimkhan.it?source=rss-94455fbaa618------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sun, 22 Nov 2026 16:35:23 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@karimkhan.it/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[Getting started with Data Science — Part 1]]></title>
            <link>https://medium.com/@karimkhan.it/getting-started-with-data-science-part-1-d29b7e5f9a84?source=rss-94455fbaa618------2</link>
            <guid isPermaLink="false">https://medium.com/p/d29b7e5f9a84</guid>
            <category><![CDATA[industry-4-0]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[deep-learning]]></category>
            <dc:creator><![CDATA[Karimkhan]]></dc:creator>
            <pubDate>Mon, 18 Apr 2022 05:57:28 GMT</pubDate>
            <atom:updated>2022-04-18T05:57:42.744Z</atom:updated>
            <content:encoded><![CDATA[<h3>Getting started with Data Science — Part 1</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*kGIwVnYRYdWe4tpFHy0-Qg.jpeg" /></figure><p>I repeated get this query regarding switching to a Data science profile. People having 10+ years of experience in sales, marketing, electronics, Mechanical and other backgrounds even have inquired about switching to the Data science field.</p><p>Many fresher students belonging to Mechanical, Electrical, ECE also ask about “How to I make my career into AI/Data Science/Analytics”</p><p>I will write two articles targeting 2 categories of audience</p><ol><li>Beginner — Fresher graduates who want to switch their career</li><li>Experienced — Experienced professional from IT/Non-IT background</li></ol><p>We all know that AI is going to be used in all sectors and it is a top technology trend wherever you read it.</p><p>We are now into <strong>Industry 4.O</strong> revolution</p><p>Industry 4.0 is revolutionizing the way companies manufacture, improve and distribute their products. Manufacturers are integrating new technologies, including Internet of Things (IoT), cloud computing and analytics, and AI and machine learning into their production facilities and throughout their operations.</p><p>So people are crazy about making their career in this field</p><p>We hire fresher and experienced candidates for Data science profiles. Based on my hiring experience I will try to show what we need in potential candidates.</p><p>Having your degree in CS/IT will surely give hire preference. Because this candidate will be 3–4 years of additional programming knowledge. But nowadays many candidates participate in online coding competitions and make their programming skills sharp, so even if you are from a non-IT background you can really make it.</p><p>So here I have listed tips and points which can surely help you to grab you dream job in AI field</p><p><strong>1. You must have programming skills. Python is the most preferred. I believe 85–90% of organizations used python, and 10–15% of organizations might be used R or other languages.</strong></p><p>If you include your online competitive programming profile links from codechef, topcoders, hackerrank etc, that will surely make positive impact.</p><p>Some courses which can help you to get the required knowledge in python</p><ul><li><a href="https://www.coursera.org/learn/python">https://www.coursera.org/learn/python</a></li><li><a href="https://www.udemy.com/course/python-core-and-advanced/">https://www.udemy.com/course/python-core-and-advanced/</a></li><li><a href="https://www.udemy.com/course/100-days-of-code/">https://www.udemy.com/course/100-days-of-code/</a></li><li><a href="https://www.udemy.com/course/complete-python-bootcamp/">https://www.udemy.com/course/complete-python-bootcamp/</a></li><li><a href="https://www.udemy.com/course/python-for-machine-learning-data-science-masterclass/">https://www.udemy.com/course/python-for-machine-learning-data-science-masterclass/</a></li></ul><p>Note — No need to have a deep focus on Python web development part. But having knowledge in python API is essential to integrating the python model with apps</p><p><strong>2. Get hands-on practice and good knowledge about algorithms, statistical analysis and logical programming. The above-listed courses will cover some part of this, but you may need to do extra courses to increase your knowledge and expertise.</strong></p><p><strong>3. Get basic knowledge in Data Science. You must know the basics of Machine learning, Deep learning, Computer vision, Natural language processing, and quantitative analysis. Read about these topics on Google, Quora, and Linkedin</strong></p><p>Not all organizations need knowledge about all of these. But wherever you apply they will ask you related to the above topics. They are interrelated. So having basic knowledge about all of them will be good for you. Here are a few helpful courses</p><ul><li><a href="https://www.coursera.org/learn/machine-learning">https://www.coursera.org/learn/machine-learning</a></li><li><a href="https://www.udemy.com/course/the-data-science-course-complete-data-science-bootcamp/">https://www.udemy.com/course/the-data-science-course-complete-data-science-bootcamp/</a></li><li><a href="https://www.udemy.com/course/intro-to-data-science/">https://www.udemy.com/course/intro-to-data-science/</a></li><li><a href="https://www.udemy.com/course/datascience/">https://www.udemy.com/course/datascience/</a></li><li><a href="https://www.udemy.com/course/python-for-data-science-and-machine-learning-bootcamp/">https://www.udemy.com/course/python-for-data-science-and-machine-learning-bootcamp/</a></li></ul><p>Apart from this, you can look out for specific courses on ML, DL, NLP, CV on udemy, and Coursera to get expertise in specific domains.</p><p><strong>4. (Not necessary) Get specialization courses in Machine Learning, Deep Learning, NLP</strong></p><ul><li><a href="https://www.deeplearning.ai/program/deep-learning-specialization/">https://www.deeplearning.ai/program/deep-learning-specialization/</a></li><li><a href="https://www.deeplearning.ai/program/practical-data-science-specialization/">https://www.deeplearning.ai/program/practical-data-science-specialization/</a></li><li><a href="https://www.deeplearning.ai/program/natural-language-processing-specialization/">https://www.deeplearning.ai/program/natural-language-processing-specialization/</a></li></ul><p>The above points will help you get the required knowledge. Once you have required skills and knowledge, now you can start building your profile</p><p><strong>5. Add at least 4 related projects to your resume</strong></p><p>Depending upon which organization you are applying to and what are their requirements, you can include specific projects in your resume. e.g. You are applying for a Computer vision opportunity, in that case, you can include image processing, video processing, and Object detection-related projects in your resume.</p><p>Include project title, brief description, link to GitHub code, tools and technologies used in each project. Add your skills as well</p><p><strong>6. Create a decent resume and update your profile on Github, Kaggle, and Linkedin</strong>.</p><p>You must know how to sell yourself. Use resume building website to build a resume in a good format.</p><p>Add whatever course assignments, or projects you have done on your GitHub. This will boost your profile. You can include your work on Linkedin, which is the best place to showcase it. Kaggle Challenge Participation experience will also give you a good rank.</p><p>Don’t worry if you are not able to complete all courses. If you get a basic knowledge, good projects, and a profile, get some confidence.</p><p>Now you are ready to apply as AI Intern, Machine Learning Engineer, Data Science Intern, and related roles.</p><p>###############</p><p>Currently, I am doing deep dive into Huge Data.</p><p>Check out my profile to read more about AI, Data Science, ML, DL, NLP</p><p><a href="https://medium.com/@karimkhan.it">https://www.linkedin.com/in/karimkhanp/recent-activity/posts/</a></p><p><a href="https://medium.com/@karimkhan.it">https://medium.com/@karimkhan.it</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=d29b7e5f9a84" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[AI / Machine Learning / Deep Learning online courses]]></title>
            <link>https://medium.com/@karimkhan.it/ai-machine-learning-deep-learning-online-courses-da9de01b8d9?source=rss-94455fbaa618------2</link>
            <guid isPermaLink="false">https://medium.com/p/da9de01b8d9</guid>
            <category><![CDATA[naturallanguageprocessing]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[online-learning]]></category>
            <dc:creator><![CDATA[Karimkhan]]></dc:creator>
            <pubDate>Thu, 07 Apr 2022 06:01:26 GMT</pubDate>
            <atom:updated>2022-04-07T06:01:26.767Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*MHBkGdQqtDG-OnhpYbCHFg.jpeg" /></figure><p>Many people ask me on a daily basis how to switch to Data Science. I feel I should write a good post on that but by that time sharing the list of online courses from decent institutes.</p><p>You can not afford to go to Stanford or Berkely or attend Andrew Ng’s lecture at Stanford.</p><p>But now it has been so easy to learn from them seating at your own desk.</p><h3>Artificial Intelligence</h3><ul><li><a href="https://cs50.harvard.edu/ai/2020/">CS50 — Introduction to Artificial Intelligence with Python (and Machine Learning), Harvard OCW</a></li><li><a href="http://www.infocobuild.com/education/audio-video-courses/computer-science/cs188-spring2015-berkeley.html">CS 188 — Introduction to Artificial Intelligence, UC Berkeley — Spring 2015</a></li><li><a href="https://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-034-artificial-intelligence-fall-2010/lecture-videos/">6.034 Artificial Intelligence, MIT OCW</a></li><li><a href="https://www.youtube.com/playlist?list=PLoROMvodv4rO1NB9TD4iUZ3qghGEGtqNX">CS221: Artificial Intelligence: Principles and Techniques — Autumn 2019 — Stanford University</a></li><li><a href="http://www.cs.cmu.edu/~zkolter/course/15-780-s14/lectures.html">15–780 — Graduate Artificial Intelligence, Spring 14, CMU</a></li><li><a href="https://courses.cs.washington.edu/courses/csep573/03wi/lectures/index.htm">CSE 592 Applications of Artificial Intelligence, Winter 2003 — University of Washington</a></li><li><a href="http://www.cs.ubc.ca/~mack/CS322/">CS322 — Introduction to Artificial Intelligence, Winter 2012–13 — UBC</a> (<a href="https://www.youtube.com/playlist?list=PLDPnGbm0sUmpzvcGvktbz446SLdFbfZVU">YouTube</a>)</li><li><a href="https://www.youtube.com/playlist?list=PLUenpfvlyoa1iiSbGy9BBewgiXjzxVgBd">CS 4804: Introduction to Artificial Intelligence, Fall 2016</a></li><li><a href="https://www.youtube.com/playlist?list=PLUenpfvlyoa0PB6_kqJ9WU7m6i6z1RhfJ">CS 5804: Introduction to Artificial Intelligence, Spring 2015</a></li><li><a href="https://nptel.ac.in/courses/106105077/">Artificial Intelligence — IIT Kharagpur</a></li><li><a href="https://nptel.ac.in/courses/106106126/">Artificial Intelligence — IIT Madras</a></li><li><a href="https://nptel.ac.in/courses/106105079/">Artificial Intelligence(Prof.P.Dasgupta) — IIT Kharagpur</a></li><li><a href="https://www.youtube.com/playlist?list=PLAwxTw4SYaPlqMkzr4xyuD6cXTIgPuzgn">MOOC — Intro to Artificial Intelligence — Udacity</a></li><li><a href="https://www.youtube.com/playlist?list=PLAwxTw4SYaPkCSYXw6-a_aAoXVKLDwnHK">MOOC — Artificial Intelligence for Robotics — Udacity</a></li><li><a href="https://www.youtube.com/playlist?list=PLbQ3Aya0VERDoDdbMogU9EASJGWris9qG">Graduate Course in Artificial Intelligence, Autumn 2012 — University of Washington</a></li><li><a href="http://groups.inf.ed.ac.uk/vision/VIDEO/2015/abs.htm">Agent-Based Systems 2015/16- University of Edinburgh</a></li><li><a href="http://groups.inf.ed.ac.uk/vision/VIDEO/2014/inf2d.htm">Informatics 2D — Reasoning and Agents 2014/15- University of Edinburgh</a></li><li><a href="https://www.youtube.com/playlist?list=PL39B5D3AFC249556A">Artificial Intelligence — Hochschule Ravensburg-Weingarten</a></li><li><a href="http://www.ifis.cs.tu-bs.de/teaching/ws-1516/KBS">Deductive Databases and Knowledge-Based Systems — Technische Universität Braunschweig, Germany</a></li><li><a href="https://nptel.ac.in/courses/106106140/">Artificial Intelligence: Knowledge Representation and Reasoning — IIT Madras</a></li><li><a href="https://www.youtube.com/playlist?list=PLoOmvuyo5UAeihlKcWpzVzB51rr014TwD">Semantic Web Technologies by Dr. Harald Sack — HPI</a></li><li><a href="https://www.youtube.com/playlist?list=PLoOmvuyo5UAcBXlhTti7kzetSsi1PpJGR">Knowledge Engineering with Semantic Web Technologies by Dr. Harald Sack — HPI</a></li><li><a href="https://sites.wustl.edu/jeffheaton/t81-558/">T81–558: Applications of Deep Neural Networks by Jeff Heaton, 2022, Washington University in St. Louis</a></li></ul><h3>Machine Learning</h3><ul><li>Introduction to Machine Learning</li><li><a href="https://www.youtube.com/playlist?list=PLLssT5z_DsK-h9vYZkQkYNWcItqhlRJLN">MOOC Machine Learning Andrew Ng — Coursera/Stanford</a> (<a href="http://www.holehouse.org/mlclass/">Notes</a>)</li><li><a href="https://course.fast.ai/ml.html">Introduction to Machine Learning for Coders</a></li><li><a href="http://www.dataschool.io/15-hours-of-expert-machine-learning-videos/">MOOC — Statistical Learning, Stanford University</a></li><li><a href="https://www.youtube.com/playlist?list=PLgKuh-lKre11GbZWneln-VZDLHyejO7YD">Foundations of Machine Learning Boot Camp, Berkeley Simons Institute</a></li><li><a href="https://www.youtube.com/playlist?list=PLuz4CTPOUNi6BfMrltePqMAHdl5W33-bC">CS155 — Machine Learning &amp; Data Mining, 2017 — Caltech</a> (<a href="http://www.yisongyue.com/courses/cs155/2017_winter/">Notes</a>) (<a href="https://www.youtube.com/playlist?list=PL5HdMttxBY0BVTP9y7qQtzTgmcjQ3P0mb">2016</a>)</li><li><a href="https://work.caltech.edu/lectures.html">CS 156 — Learning from Data, Caltech</a></li><li><a href="http://www.cs.cmu.edu/~ninamf/courses/601sp15/lectures.shtml">10–601 — Introduction to Machine Learning (MS) — Tom Mitchell — 2015, CMU</a> (<a href="https://www.youtube.com/playlist?list=PLAJ0alZrN8rD63LD0FkzKFiFgkOmEtltQ">YouTube</a>)</li><li><a href="https://www.youtube.com/playlist?list=PL7k0r4t5c10-g7CWCnHfZOAxLaiNinChk">10–601 Machine Learning | CMU | Fall 2017</a></li><li><a href="http://www.cs.cmu.edu/~tom/10701_sp11/lectures.shtml">10–701 — Introduction to Machine Learning (PhD) — Tom Mitchell, Spring 2011, CMU</a> (<a href="https://www.youtube.com/playlist?list=PL7y-1rk2cCsDZCVz2xS7LrExqidHpJM3B">Fall 2014</a>) (<a href="https://www.youtube.com/playlist?list=PLZSO_6-bSqHTTV7w9u7grTXBHMH-mw3qn">Spring 2015 by Alex Smola</a>)</li><li><a href="https://www.youtube.com/playlist?list=PLpqQKYIU-snAPM89YPPwyQ9xdaiAdoouk">10–301/601 — Introduction to Machine Learning — Spring 2020 — CMU</a></li><li><a href="https://www.youtube.com/playlist?list=PLVNifWxslHCDlbyitaLLYBOAEPbmF1AHg">CMS 165 Foundations of Machine Learning and Statistical Inference — 2020 — Caltech</a></li><li><a href="https://www.youtube.com/playlist?list=PL34iyE0uXtxo7vPXGFkmm6KbgZQwjf9Kf">Microsoft Research — Machine Learning Course</a></li><li><a href="https://courses.engr.illinois.edu/cs446/sp2019/AGS/_site/">CS 446 — Machine Learning, Spring 2019, UIUC</a> (<a href="https://www.youtube.com/playlist?list=PLQcasX5-oG91TgY6A_gz-IW7YSpwdnD2O">Fall 2016 Lectures</a>)</li><li><a href="https://www.youtube.com/playlist?list=PLE6Wd9FR--Ecf_5nCbnSQMHqORpiChfJf">undergraduate machine learning at UBC 2012, Nando de Freitas</a></li><li><a href="https://see.stanford.edu/Course/CS229">CS 229 — Machine Learning — Stanford University</a> (<a href="https://www.youtube.com/playlist?list=PLoROMvodv4rMiGQp3WXShtMGgzqpfVfbU">Autumn 2018</a>)</li><li><a href="https://people.eecs.berkeley.edu/~jrs/189/">CS 189/289A Introduction to Machine Learning, Prof Jonathan Shewchuk — UCBerkeley</a></li><li><a href="https://www.youtube.com/playlist?list=PLWmXHcz_53Q02ZLeAxigki1JZFfCO6M-b">CPSC 340: Machine Learning and Data Mining (2018) — UBC</a></li><li><a href="http://www.cs.cornell.edu/courses/cs4780/2013fa/">CS4780/5780 Machine Learning, Fall 2013 — Cornell University</a></li><li><a href="http://www.cs.cornell.edu/courses/cs4780/2018fa/page18/index.html">CS4780/5780 Machine Learning, Fall 2018 — Cornell University</a> (<a href="https://www.youtube.com/playlist?list=PLl8OlHZGYOQ7bkVbuRthEsaLr7bONzbXS">Youtube</a>)</li><li><a href="https://www.youtube.com/playlist?list=PLEQDy5tl3xkMzk_zlo2DPzXteCquHA8bQ">CSE474/574 Introduction to Machine Learning — SUNY University at Buffalo</a></li><li><a href="https://www.youtube.com/playlist?list=PLbuogVdPnkCozRSsdueVwX7CF9N4QWL0B">CS 5350/6350 — Machine Learning, Fall 2016, University of Utah</a></li><li><a href="https://filebox.ece.vt.edu/~s15ece5984/">ECE 5984 Introduction to Machine Learning, Spring 2015 — Virginia Tech</a></li><li><a href="https://www.youtube.com/playlist?list=PLUenpfvlyoa0rMoE5nXA8kdctBKE9eSob">CSx824/ECEx242 Machine Learning, Bert Huang, Fall 2015 — Virginia Tech</a></li><li><a href="http://www.cs.toronto.edu/~rsalakhu/STA4273_2015/lectures.html">STA 4273H — Large Scale Machine Learning, Winter 2015 — University of Toronto</a></li><li><a href="https://www.youtube.com/channel/UCR4_akQ1HYMUcDszPQ6jh8Q/videos">CS 485/685 Machine Learning, Shai Ben-David, University of Waterloo</a></li><li><a href="https://www.youtube.com/playlist?list=PLehuLRPyt1HzXDemu7K4ETcF0Ld_B5adG">STAT 441/841 Classification Winter 2017 , Waterloo</a></li><li><a href="https://www.youtube.com/channel/UCIE4UdPoCJZMAZrTLuq-CPQ/videos">10–605 — Machine Learning with Large Datasets, Fall 2016 — CMU</a></li><li><a href="https://www.youtube.com/playlist?list=PLruBu5BI5n4aFpG32iMbdWoRVAA-Vcso6">Information Theory, Pattern Recognition, and Neural Networks — University of Cambridge</a></li><li><a href="https://www.youtube.com/playlist?list=PLVxFQjPUB2cnYGZPAGG52OQc9SpWVKjjB">Python and machine learning — Stanford Crowd Course Initiative</a></li><li><a href="https://www.youtube.com/playlist?list=PLAwxTw4SYaPl0N6-e1GvyLp5-MUMUjOKo">MOOC — Machine Learning Part 1a — Udacity/Georgia Tech</a> (<a href="https://www.youtube.com/playlist?list=PLAwxTw4SYaPlkESDcHD-0oqVx5sAIgz7O">Part 1b</a> <a href="https://www.youtube.com/playlist?list=PLAwxTw4SYaPmaHhu-Lz3mhLSj-YH-JnG7">Part 2</a> <a href="https://www.youtube.com/playlist?list=PLAwxTw4SYaPnidDwo9e2c7ixIsu_pdSNp">Part 3</a>)</li><li><a href="http://groups.inf.ed.ac.uk/vision/VIDEO/2015/mlpr.htm">Machine Learning and Pattern Recognition 2015/16- University of Edinburgh</a></li><li><a href="http://groups.inf.ed.ac.uk/vision/VIDEO/2015/iaml.htm">Introductory Applied Machine Learning 2015/16- University of Edinburgh</a></li><li><a href="https://www.youtube.com/playlist?list=PLuRaSnb3n4kRDZVU6wxPzGdx1CN12fn0w">Pattern Recognition Class (2012)- Universität Heidelberg</a></li><li><a href="https://www.youtube.com/playlist?list=PLcXJymqaE9PPGGtFsTNoDWKl-VNVX5d6b">Introduction to Machine Learning and Pattern Recognition — CBCSL OSU</a></li><li><a href="https://nptel.ac.in/courses/106105152/">Introduction to Machine Learning — IIT Kharagpur</a></li><li><a href="https://nptel.ac.in/courses/106106139/">Introduction to Machine Learning — IIT Madras</a></li><li><a href="https://nptel.ac.in/courses/117108048/">Pattern Recognition — IISC Bangalore</a></li><li><a href="https://nptel.ac.in/courses/117105101/">Pattern Recognition and Application — IIT Kharagpur</a></li><li><a href="https://nptel.ac.in/courses/106106046/">Pattern Recognition — IIT Madras</a></li><li><a href="https://www.youtube.com/playlist?list=PLqJm7Rc5-EXFv6RXaPZzzlzo93Hl0v91E">Machine Learning Summer School 2013 — Max Planck Institute for Intelligent Systems Tübingen</a></li><li><a href="https://www.youtube.com/playlist?list=PLauepKFT6DK_1_plY78bXMDj-bshv7UsQ">Machine Learning — Professor Kogan (Spring 2016) — Rutgers</a></li><li><a href="http://sli.ics.uci.edu/Classes/2015W-273a">CS273a: Introduction to Machine Learning</a> (<a href="https://www.youtube.com/playlist?list=PLkWzaBlA7utJMRi89i9FAKMopL0h0LBMk">YouTube</a>)</li><li><a href="https://www.youtube.com/playlist?list=PLyGKBDfnk-iD5dK8N7UBUFVVDBBtznenR">Machine Learning Crash Course 2015</a></li><li><a href="http://inverseprobability.com/mlai2015/">COM4509/COM6509 Machine Learning and Adaptive Intelligence 2015–16</a></li><li><a href="https://sites.google.com/site/10715advancedmlintro2017f/lectures">10715 Advanced Introduction to Machine Learning</a></li><li><a href="https://www.youtube.com/playlist?list=PLzn6LN6WhlN273tsqyfdrBUsA-o5nUESV">Introduction to Machine Learning — Spring 2018 — ETH Zurich</a></li><li><a href="https://www.youtube.com/user/UWCSE/playlists?view=50&amp;sort=dd&amp;shelf_id=16">Machine Learning — Pedro Domingos- University of Washington</a></li><li><a href="https://www.youtube.com/playlist?list=PLY-OA_xnxFwSe98pzMGVR4bjAZZYrNT7L">Advanced Machine Learning — 2019 — ETH Zürich</a></li><li><a href="https://www.youtube.com/playlist?list=PLyH-5mHPFffFwz7Twap0XuVeUJ8vuco9t">Machine Learning (COMP09012)</a></li><li><a href="https://www.youtube.com/playlist?list=PL05umP7R6ij1tHaOFY96m5uX3J21a6yNd">Probabilistic Machine Learning 2020 — University of Tübingen</a></li><li><a href="https://www.youtube.com/playlist?list=PL05umP7R6ij2XCvrRzLokX6EoHWaGA2cC">Statistical Machine Learning 2020 — Ulrike von Luxburg — University of Tübingen</a></li><li><a href="https://www.cs.columbia.edu/~amueller/comsw4995s20/schedule/">COMS W4995 — Applied Machine Learning — Spring 2020 — Columbia University</a></li><li><a href="https://apmonitor.com/pds">Machine Learning for Engineers 2022</a> (<a href="https://www.youtube.com/watch?v=Gh5rbBLh4JY&amp;list=PLLBUgWXdTBDg1K1bu60lHypSzSP-WSBmx">YouTube</a>)</li></ul><h3>Data Mining</h3><ul><li><a href="https://courses.cs.washington.edu/courses/csep546/16sp/">CSEP 546, Data Mining — Pedro Domingos, Sp 2016 — University of Washington</a> (<a href="https://www.youtube.com/playlist?list=PLTPQEx-31JXgtDaC6-3HxWcp7fq4N8YGr">YouTube</a>)</li><li><a href="https://www.cs.utah.edu/~jeffp/teaching/cs5140.html">CS 5140/6140 — Data Mining, Spring 2016, University of Utah</a> (<a href="https://www.youtube.com/playlist?list=PLbuogVdPnkCpXfb43Wvc7s5fXWzedwTPB">Youtube</a>)</li><li><a href="http://www.cs.utah.edu/~jeffp/teaching/cs5955.html">CS 5955/6955 — Data Mining, University of Utah</a> (<a href="https://www.youtube.com/channel/UCcrlwW88yMcXujhGjSP2WBg/videos">YouTube</a>)</li><li><a href="http://www.stats202.com/original_index.html">Statistics 202 — Statistical Aspects of Data Mining, Summer 2007 — Google</a> (<a href="https://www.youtube.com/playlist?list=PLFE776F2C513A744E">YouTube</a>)</li><li><a href="https://www.youtube.com/playlist?list=PLLssT5z_DsK8Xwnh_0bjN4KNT81bekvtt">MOOC — Text Mining and Analytics by ChengXiang Zhai</a></li><li><a href="https://itunes.apple.com/us/itunes-u/information-retrieval-ss-2014/id874200291">Information Retrieval SS 2014, iTunes — HPI</a></li><li><a href="https://www.youtube.com/playlist?list=PLm4W7_iX_v4NqPUjceOGd-OKNVO4c_cPD">MOOC — Data Mining with Weka</a></li><li><a href="https://www.youtube.com/playlist?list=PLB4CCA346A5741C4C">CS 290 DataMining Lectures</a></li><li><a href="https://web.stanford.edu/class/cs246/">CS246 — Mining Massive Data Sets, Winter 2016, Stanford University</a> (<a href="https://www.youtube.com/channel/UC_Oao2FYkLAUlUVkBfze4jg/videos">YouTube</a>)</li><li><a href="https://www.youtube.com/playlist?list=PLY-OA_xnxFwRHZO6L6yT253VPgrZazQs6">Data Mining: Learning From Large Datasets — Fall 2017 — ETH Zurich</a></li><li><a href="https://www.youtube.com/playlist?list=PLzn6LN6WhlN1ktkDvNurPSDwTQ_oGQisn">Information Retrieval — Spring 2018 — ETH Zurich</a></li><li><a href="http://www.cse.fau.edu/~taghi/classes/cap6673/">CAP6673 — Data Mining and Machine Learning — FAU</a>(<a href="https://vimeo.com/album/1505953">Video lectures</a>)</li><li><a href="http://www.ifis.cs.tu-bs.de/teaching/ws-1617/dwh">Data Warehousing and Data Mining Techniques — Technische Universität Braunschweig, Germany</a></li></ul><h3>Data Science</h3><ul><li><a href="http://data8.org/">Data 8: The Foundations of Data Science — UC Berkeley</a> (<a href="http://data8.org/su17/">Summer 17</a>)</li><li><a href="https://www.youtube.com/playlist?list=PLOtl7M3yp-DVBdLYatrltDJr56AKZ1qXo">CSE519 — Data Science Fall 2016 — Skiena, SBU</a></li><li><a href="http://cs109.github.io/2015/pages/videos.html">CS 109 Data Science, Harvard University</a> (<a href="https://www.youtube.com/playlist?list=PLb4G5axmLqiuneCqlJD2bYFkBwHuOzKus">YouTube</a>)</li><li><a href="https://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-0002-introduction-to-computational-thinking-and-data-science-fall-2016/lecture-videos/">6.0002 Introduction to Computational Thinking and Data Science — MIT OCW</a></li><li><a href="https://www.youtube.com/playlist?list=PLPHXc20GewP8J56CisONS_mFZWZAfa7jR">Data 100 — Summer 19- UC Berkeley</a></li><li><a href="https://www.tele-task.de/series/1179/">Distributed Data Analytics (WT 2017/18) — HPI University of Potsdam</a></li><li><a href="https://www.youtube.com/playlist?list=PL-XXv-cvA_iDsSPnMJlnhIyADGUmikoIO">Statistics 133 — Concepts in Computing with Data, Fall 2013 — UC Berkeley</a></li><li><a href="https://www.tele-task.de/series/1027/">Data Profiling and Data Cleansing (WS 2014/15) — HPI University of Potsdam</a></li><li><a href="http://am207.github.io/2016/index.html">AM 207 — Stochastic Methods for Data Analysis, Inference and Optimization, Harvard University</a></li><li><a href="http://people.seas.harvard.edu/~minilek/cs229r/fall15/lec.html">CS 229r — Algorithms for Big Data, Harvard University</a> (<a href="https://www.youtube.com/playlist?list=PL2SOU6wwxB0v1kQTpqpuu5kEJo2i-iUyf">Youtube</a>)</li><li><a href="https://nptel.ac.in/courses/106106142/">Algorithms for Big Data — IIT Madras</a></li><li><a href="https://github.com/APMonitor/data_science">Python Data Science with the TCLab</a> (<a href="https://www.youtube.com/watch?v=pAgW_bZVo88&amp;list=PLLBUgWXdTBDg1Qgmwt4jKtVn9BWh5-zgy">YouTube</a>)</li><li>Probabilistic Graphical Modeling</li><li><a href="https://www.youtube.com/playlist?list=PLvfF4UFg6Ejj6SX-ffw-O4--SPbB9P7eP">MOOC — Probabilistic Graphical Models — Coursera</a></li><li><a href="https://www.youtube.com/playlist?list=PLbuogVdPnkCpvxdF-Gy3gwaBObx7AnQut">CS 6190 — Probabilistic Modeling, Spring 2016, University of Utah</a></li><li><a href="https://www.cs.cmu.edu/~epxing/Class/10708-20/lectures.html">10–708 — Probabilistic Graphical Models, Carnegie Mellon University</a></li><li><a href="http://openclassroom.stanford.edu/MainFolder/CoursePage.php?course=ProbabilisticGraphicalModels">Probabilistic Graphical Models, Daphne Koller, Stanford University</a></li><li><a href="https://www.cs.helsinki.fi/en/courses/582636/2015/K/K/1">Probabilistic Models — UNIVERSITY OF HELSINKI</a></li><li><a href="http://groups.inf.ed.ac.uk/vision/VIDEO/2015/pmr.htm">Probabilistic Modelling and Reasoning 2015/16- University of Edinburgh</a></li><li><a href="https://www.youtube.com/playlist?list=PLd-PuDzW85AcV4bgdu7wHPL37hm60W4RM">Probabilistic Graphical Models, Spring 2018 — Notre Dame</a></li></ul><h3>Deep Learning</h3><ul><li><a href="https://www.youtube.com/playlist?list=PLLHTzKZzVU9eaEyErdV26ikyolxOsz6mq">NYU Deep Learning Spring 2020</a></li><li><a href="https://www.youtube.com/playlist?list=PLLHTzKZzVU9e6xUfG10TkTWApKSZCzuBI">NYU Deep Learning Spring 2021</a></li><li><a href="http://introtodeeplearning.com/">6.S191: Introduction to Deep Learning — MIT</a></li><li><a href="https://www.youtube.com/channel/UC8hYZGEkI2dDO8scT8C5UQA/videos">Deep Learning CMU</a></li><li><a href="https://course.fast.ai/">Part 1: Practical Deep Learning for Coders, v3 — fast.ai</a></li><li><a href="https://course19.fast.ai/part2">Part 2: Deep Learning from the Foundations — fast.ai</a></li><li><a href="https://www.youtube.com/playlist?list=PLE6Wd9FR--EfW8dtjAuPoTuPcqmOV53Fu">Deep learning at Oxford 2015 — Nando de Freitas</a></li><li><a href="https://uni-tuebingen.de/fakultaeten/mathematisch-naturwissenschaftliche-fakultaet/fachbereiche/informatik/lehrstuehle/autonomous-vision/lectures/self-driving-cars/">Self-Driving Cars — Andreas Geiger, 2021/22</a> (<a href="https://www.youtube.com/watch?v=wAaSJUAKPuY&amp;list=PL05umP7R6ij321zzKXK6XCQXAaaYjQbzr">YouTube</a>)</li><li><a href="https://www.youtube.com/playlist?list=PLrAXtmErZgOeiKm4sgNOknGvNjby9efdf">6.S094: Deep Learning for Self-Driving Cars — MIT</a></li><li><a href="https://bcourses.berkeley.edu/courses/1453965/pages/cs294-129-designing-visualizing-and-understanding-deep-neural-networks">CS294–129 Designing, Visualizing and Understanding Deep Neural Networks</a> (<a href="https://www.youtube.com/playlist?list=PLkFD6_40KJIxopmdJF_CLNqG3QuDFHQUm">YouTube</a>)</li><li><a href="https://www.youtube.com/playlist?list=PLoROMvodv4rOABXSygHTsbvUz4G_YQhOb">CS230: Deep Learning — Autumn 2018 — Stanford University</a></li><li><a href="https://www.youtube.com/playlist?list=PLZSO_6-bSqHQHBCoGaObUljoXAyyqhpFW">STAT-157 Deep Learning 2019 — UC Berkeley</a></li><li><a href="https://www.youtube.com/playlist?list=PL_Ig1a5kxu5645uORPL8xyvHr91Lg8G1l">Full Stack DL Bootcamp 2019 — UC Berkeley</a></li><li><a href="http://openclassroom.stanford.edu/MainFolder/CoursePage.php?course=DeepLearning">Deep Learning, Stanford University</a></li><li><a href="https://www.youtube.com/playlist?list=PLoRl3Ht4JOcdU872GhiYWf6jwrk_SNhz9">MOOC — Neural Networks for Machine Learning, Geoffrey Hinton 2016 — Coursera</a></li><li><a href="https://www.youtube.com/playlist?list=PLwRJQ4m4UJjPiJP3691u-qWwPGVKzSlNP">Deep Unsupervised Learning — Berkeley Spring 2020</a></li><li><a href="https://www.youtube.com/playlist?list=PLehuLRPyt1Hyi78UOkMPWCGRxGcA9NVOE">Stat 946 Deep Learning — University of Waterloo</a></li><li><a href="http://info.usherbrooke.ca/hlarochelle/neural_networks/content.html">Neural networks class — Université de Sherbrooke</a> (<a href="https://www.youtube.com/playlist?list=PL6Xpj9I5qXYEcOhn7TqghAJ6NAPrNmUBH">YouTube</a>)</li><li><a href="https://www.youtube.com/channel/UCf4SX8kAZM_oGcZjMREsU9w/videos">CS294–158 Deep Unsupervised Learning SP19</a></li><li><a href="https://www.youtube.com/playlist?list=PL-5eMc3HQTBavDoZpFcX-bff5WgQqSLzR">DLCV — Deep Learning for Computer Vision — UPC Barcelona</a></li><li><a href="https://www.youtube.com/playlist?list=PL-5eMc3HQTBagIUjKefjcTbnXC0wXC_vd">DLAI — Deep Learning for Artificial Intelligence @ UPC Barcelona</a></li><li><a href="https://nptel.ac.in/courses/117105084/">Neural Networks and Applications — IIT Kharagpur</a></li><li><a href="http://uvadlc.github.io/#lecture">UVA DEEP LEARNING COURSE</a></li><li><a href="https://www.youtube.com/playlist?list=PLTIkHmXc-7an8xbwhAJX-LQ4D4Uf-ar5I">Nvidia Machine Learning Class</a></li><li><a href="https://www.youtube.com/playlist?list=PL05umP7R6ij3NTWIdtMbfvX7Z-4WEXRqD">Deep Learning — Winter 2020–21 — Tübingen Machine Learning</a></li></ul><h3>Reinforcement Learning</h3><ul><li><a href="https://www.youtube.com/playlist?list=PLoROMvodv4rOSOPzutgyCTapiGlY2Nd8u">CS234: Reinforcement Learning — Winter 2019 — Stanford University</a></li><li><a href="https://www.youtube.com/playlist?list=PLqYmG7hTraZDM-OYHWgPebj2MfCFzFObQ">Introduction to reinforcement learning — UCL</a></li><li><a href="https://www.youtube.com/playlist?list=PLqYmG7hTraZDNJre23vqCGIVpfZ_K2RZs">Advanced Deep Learning &amp; Reinforcement Learning — UCL</a></li><li><a href="https://www.youtube.com/playlist?list=PLyqSpQzTE6M_FwzHFAyf4LSkz_IjMyjD9">Reinforcement Learning — IIT Madras</a></li><li><a href="https://www.youtube.com/playlist?list=PLdAoL1zKcqTXFJniO3Tqqn6xMBBL07EDc">CS885 Reinforcement Learning — Spring 2018 — University of Waterloo</a></li><li><a href="https://www.youtube.com/playlist?list=PLkFD6_40KJIwhWJpGazJ9VSj9CFMkb79A">CS 285 — Deep Reinforcement Learning- UC Berkeley</a></li><li><a href="https://www.youtube.com/playlist?list=PLkFD6_40KJIxJMR-j5A1mkxK26gh_qg37">CS 294 112 — Reinforcement Learning</a></li><li><a href="https://www.youtube.com/playlist?list=PLllwxvcS7ca5wOmRLKm6ri-OaC0INYehv">NUS CS 6101 — Deep Reinforcement Learning</a></li><li><a href="https://www.youtube.com/playlist?list=PL_Nk3YvgORJs1tCLQnlnSRsOJArj_cP9u">ECE 8851: Reinforcement Learning</a></li><li><a href="http://rll.berkeley.edu/deeprlcourse/">CS294–112, Deep Reinforcement Learning Sp17</a> (<a href="https://www.youtube.com/playlist?list=PLkFD6_40KJIwTmSbCv9OVJB3YaO4sFwkX">YouTube</a>)</li><li><a href="http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html">UCL Course 2015 on Reinforcement Learning by David Silver from DeepMind</a> (<a href="https://www.youtube.com/watch?v=2pWv7GOvuf0">YouTube</a>)</li><li><a href="https://sites.google.com/view/deep-rl-bootcamp/lectures">Deep RL Bootcamp — Berkeley Aug 2017</a></li><li><a href="https://www.youtube.com/playlist?list=PLyqSpQzTE6M_FwzHFAyf4LSkz_IjMyjD9">Reinforcement Learning — IIT Madras</a></li></ul><h3>Advanced Machine Learning</h3><ul><li><a href="https://www.youtube.com/playlist?list=PLE6Wd9FR--EdyJ5lbFl8UuGjecvVw66F6">Machine Learning 2013 — Nando de Freitas, UBC</a></li><li><a href="https://www.cs.ox.ac.uk/people/nando.defreitas/machinelearning/">Machine Learning, 2014–2015, University of Oxford</a></li><li><a href="https://www.stat.cmu.edu/~ryantibs/statml/">10–702/36–702 — Statistical Machine Learning — Larry Wasserman, Spring 2016, CMU</a> (<a href="https://www.youtube.com/playlist?list=PLjbUi5mgii6BWEUZf7He6nowWvGne_Y8r">Spring 2015</a>)</li><li><a href="http://www.cs.cmu.edu/~bapoczos/Classes/ML10715_2015Fall/">10–715 Advanced Introduction to Machine Learning — CMU</a> (<a href="https://www.youtube.com/playlist?list=PL4DwY1suLMkcu-wytRDbvBNmx57CdQ2pJ">YouTube</a>)</li><li><a href="http://alex.smola.org/teaching/berkeley2012/syllabus.html">CS 281B — Scalable Machine Learning, Alex Smola, UC Berkeley</a></li><li><a href="https://www.youtube.com/playlist?list=PLB3sDpSRdrOvI1hYXNsa6Lety7K8FhPpx">18.409 Algorithmic Aspects of Machine Learning Spring 2015 — MIT</a></li><li><a href="https://cs330.stanford.edu/">CS 330 — Deep Multi-Task and Meta Learning — Fall 2019 — Stanford University</a> (<a href="https://www.youtube.com/playlist?list=PLoROMvodv4rMC6zfYmnD7UG3LVvwaITY5">Youtube</a>)</li></ul><h3>ML based Natural Language Processing and Computer Vision</h3><ul><li><a href="http://web.stanford.edu/class/cs224n/">CS 224N — Deep Learning for Natural Language Processing, Stanford University</a> (<a href="https://www.youtube.com/playlist?list=PLoROMvodv4rOSH4v6133s9LFPRHjEmbmJ">Lectures — Youtube</a>)</li><li><a href="https://web.stanford.edu/~jurafsky/NLPCourseraSlides.html">CS 224N — Natural Language Processing, Stanford University</a> (<a href="https://www.youtube.com/playlist?list=PLLssT5z_DsK8HbD2sPcUIDfQ7zmBarMYv">Lecture videos</a>)</li><li><a href="https://www.youtube.com/channel/UC_48v322owNVtORXuMeRmpA/playlists?view=50&amp;sort=dd&amp;shelf_id=2">CS 124 — From Languages to Information — Stanford University</a></li><li><a href="https://www.youtube.com/playlist?list=PL6397E4B26D00A269">MOOC — Natural Language Processing, Dan Jurafsky &amp; Chris Manning — Coursera</a></li><li><a href="https://www.youtube.com/playlist?list=PLtmWHNX-gukKocXQOkQjuVxglSDYWsSh9">fast.ai Code-First Intro to Natural Language Processing</a> (<a href="https://github.com/fastai/course-nlp">Github</a>)</li><li><a href="https://www.youtube.com/playlist?list=PLLssT5z_DsK8BdawOVCCaTCO99Ya58ryR">MOOC — Natural Language Processing — Coursera, University of Michigan</a></li><li><a href="https://www.youtube.com/playlist?list=PL3FW7Lu3i5JvHM8ljYj-zLfQRF3EO8sYv">CS 231n — Convolutional Neural Networks for Visual Recognition, Stanford University</a></li><li><a href="https://www.youtube.com/playlist?list=PLoROMvodv4rObpMCir6rNNUlFAn56Js20">CS224U: Natural Language Understanding — Spring 2019 — Stanford University</a></li><li><a href="https://github.com/oxford-cs-deepnlp-2017/lectures">Deep Learning for Natural Language Processing, 2017 — Oxford University</a></li><li><a href="https://vision.in.tum.de/teaching/ws2013/ml_ws13">Machine Learning for Robotics and Computer Vision, WS 2013/2014 — TU München</a> (<a href="https://www.youtube.com/playlist?list=PLTBdjV_4f-EIiongKlS9OKrBEp8QR47Wl">YouTube</a>)</li><li><a href="http://groups.inf.ed.ac.uk/vision/VIDEO/2015/inf1cs.htm">Informatics 1 — Cognitive Science 2015/16- University of Edinburgh</a></li><li><a href="http://www.inf.ed.ac.uk/teaching/courses/inf2a/schedule.html">Informatics 2A — Processing Formal and Natural Languages 2016–17 — University of Edinburgh</a></li><li><a href="http://groups.inf.ed.ac.uk/vision/VIDEO/2015/ccs.htm">Computational Cognitive Science 2015/16- University of Edinburgh</a></li><li><a href="http://groups.inf.ed.ac.uk/vision/VIDEO/2015/anlp.htm">Accelerated Natural Language Processing 2015/16- University of Edinburgh</a></li><li><a href="https://nptel.ac.in/courses/106101007/">Natural Language Processing — IIT Bombay</a></li><li><a href="https://nptel.ac.in/courses/108/105/108105103/">NOC:Deep Learning For Visual Computing — IIT Kharagpur</a></li><li><a href="https://www.youtube.com/playlist?list=PL8PYTP1V4I8Ajj7sY6sdtmjgkt7eo2VMs">CS 11–747 — Neural Nets for NLP — 2019 — CMU</a></li><li><a href="https://www.youtube.com/playlist?list=PLA212ij5XG8OTDRl8IWFiJgHR9Ve2k9pv">Natural Language Processing — Michael Collins — Columbia University</a></li><li><a href="https://www.youtube.com/playlist?list=PL5-TkQAfAZFbzxjBHtzdVCWE0Zbhomg7r">Deep Learning for Computer Vision — University of Michigan</a></li><li><a href="https://www.youtube.com/playlist?list=PL8PYTP1V4I8CHhppU6n1Q9-04m96D9gt5">CMU CS11–737 — Multilingual Natural Language Processing</a></li></ul><h3>Time Series Analysis</h3><ul><li><a href="https://www.youtube.com/playlist?list=PLtiTxpFJ4k6TZ0g496fVcQpt_-XJRNkbi">02417 Time Series Analysis</a></li><li><a href="https://www.youtube.com/playlist?list=PLl0FT6O_WWDBm-4W-eoK34omYmEMseQDX">Applied Time Series Analysis</a></li></ul><h3>Misc Machine Learning Topics</h3><ul><li><a href="http://web.stanford.edu/class/ee364a/videos.html">EE364a: Convex Optimization I — Stanford University</a></li><li><a href="https://www.youtube.com/playlist?list=PLbuogVdPnkCpRvi-qSMCdOwyn4UYoPxTI">CS 6955 — Clustering, Spring 2015, University of Utah</a></li><li><a href="http://blogs.ischool.berkeley.edu/i290-abdt-s12/">Info 290 — Analyzing Big Data with Twitter, UC Berkeley school of information</a> (<a href="https://www.youtube.com/playlist?list=PLE8C1256A28C1487F">YouTube</a>)</li><li><a href="http://www.stat.cmu.edu/~ryantibs/convexopt-S15/">10–725 Convex Optimization, Spring 2015 — CMU</a></li><li><a href="http://www.stat.cmu.edu/~ryantibs/convexopt/">10–725 Convex Optimization: Fall 2016 — CMU</a></li><li><a href="http://granite.ices.utexas.edu/coursewiki/index.php/Main_Page">CAM 383M — Statistical and Discrete Methods for Scientific Computing, University of Texas</a></li><li><a href="https://www.youtube.com/playlist?list=PLoROMvodv4rPLKxIpqhjhPgdQy7imNkDn">CS224W Machine Learning with Graphs | Spring 2021 | Stanford University</a></li><li><a href="https://www.youtube.com/playlist?list=PLyGKBDfnk-iDj3FBd0Avr_dLbrU8VG73O">9.520 — Statistical Learning Theory and Applications, Fall 2015 — MIT</a></li><li><a href="https://www.youtube.com/playlist?list=PLacBNHqv7n9gp9cBMrA6oDbzz_8JqhSKo">Reinforcement Learning — UCL</a></li><li><a href="http://academictorrents.com/details/493251615310f9b6ae1f483126292378137074cd">Regularization Methods for Machine Learning 2016</a> (<a href="https://www.youtube.com/playlist?list=PLbF0BXX_6CPJ20Gf_KbLFnPWjFTvvRwCO">YouTube</a>)</li><li><a href="http://fields2015bigdata2inference.weebly.com/materials.html">Statistical Inference in Big Data — University of Toronto</a></li><li><a href="http://www.cs.cmu.edu/~ggordon/10725-F12/schedule.html">10–725 Optimization Fall 2012 — CMU</a></li><li><a href="http://www.cs.cmu.edu/~suvrit/teach/aopt.html">10–801 Advanced Optimization and Randomized Methods — CMU</a> (<a href="https://www.youtube.com/playlist?list=PLjTcdlvIS6cjdA8WVXNIk56X_SjICxt0d">YouTube</a>)</li><li><a href="http://groups.inf.ed.ac.uk/vision/VIDEO/2015/rl.htm">Reinforcement Learning 2015/16- University of Edinburgh</a></li><li><a href="https://nptel.ac.in/courses/106106143/">Reinforcement Learning — IIT Madras</a></li><li><a href="https://www.youtube.com/playlist?list=PLDcUM9US4XdMdZOhJWJJD4mDBMnbTWw_z">Statistical Rethinking Winter 2015 — Richard McElreath</a></li><li><a href="http://marsyas.cs.uvic.ca/mirBook/course/">Music Information Retrieval — University of Victoria, 2014</a></li><li><a href="https://www.youtube.com/playlist?list=PL2A65507F7D725EFB">PURDUE Machine Learning Summer School 2011</a></li><li><a href="https://bloomberg.github.io/foml/#home">Foundations of Machine Learning — Blmmoberg Edu</a></li><li><a href="https://www.youtube.com/playlist?list=PLqYmG7hTraZDM-OYHWgPebj2MfCFzFObQ">Introduction to reinforcement learning — UCL</a></li><li><a href="https://www.youtube.com/playlist?list=PLqYmG7hTraZDNJre23vqCGIVpfZ_K2RZs">Advanced Deep Learning &amp; Reinforcement Learning — UCL</a></li><li><a href="https://www.youtube.com/playlist?list=PLAQopGWlIcya-9yzQ8c8UtPOuCv0mFZkr">Web Information Retrieval (Proff. L. Becchetti — A. Vitaletti)</a></li><li><a href="https://www.tele-task.de/series/1286/">Big Data Systems (WT 2019/20) — Prof. Dr. Tilmann Rabl — HPI</a></li><li><a href="https://www.tele-task.de/series/1179/">Distributed Data Analytics (WT 2017/18) — Dr. Thorsten Papenbrock — HPI</a></li></ul><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=da9de01b8d9" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Data-Centric AI Approach vs Code Centric AI Approach]]></title>
            <link>https://medium.com/@karimkhan.it/data-centric-ai-approach-vs-code-centric-ai-approach-9a8a3b6d5641?source=rss-94455fbaa618------2</link>
            <guid isPermaLink="false">https://medium.com/p/9a8a3b6d5641</guid>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[data-centric-ai]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[machine-learning]]></category>
            <dc:creator><![CDATA[Karimkhan]]></dc:creator>
            <pubDate>Wed, 06 Apr 2022 06:07:21 GMT</pubDate>
            <atom:updated>2022-04-06T06:07:21.724Z</atom:updated>
            <content:encoded><![CDATA[<p>In most AI projects we usually focus on code i.e. algorithm training and fine-tuning to build the model. For the last many years we are following the same conventional approach to downloading datasets and working on the code. But nowadays code aspect of any AI system is mostly a solved problem. We can easily get code from Github and Kaggle that works well enough for the required project. Rather than spending time on the algorithms, in many instances, it’s not more helpful to work on the data. Systematically going through the dataset using Exploratory data analysis processes and principles.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/624/0*yVOpI2iLA_oH2ViQ" /></figure><p>Data-Centric AI is an emerging technology approach in AI. The evolution of a new approach typically begins with a handful of experts performing the techniques intuitively. When these experts discuss and publish their ideas, these principles become more widespread and finally, tools are developed to make their application more systematic and available to everyone.</p><p>I remember Dr. Manish Gupte ( <a href="https://www.linkedin.com/in/dr-manish-gupte-b825759/">https://www.linkedin.com/in/dr-manish-gupte-b825759/</a> ) talking about the Data-driven AI approach in 2016 during one of our AI project, when I was mainly focused on the code-based approach. But Data-driven AI approach created a win situation for us.</p><p>Andrew Ng started to talk about Data-Centric AI in a <a href="https://www.youtube.com/watch?v=06-AZXmwHjo">YouTube video</a> on March 24, 2021 and since then We’ve noticed the phrase popping up on more and more corporate websites.</p><p>Here are the main points which should be taken care while following Data-Centric AI approach</p><ol><li>Make the labels y consistent</li></ol><p>It is much easier for a learning algorithm to learn a task if there is some deterministic — meaning non-random — function mapping from the inputs x to the outputs y, and the labels are consistent with this function. I</p><p>2. Use multiple labelers to spot inconsistencies</p><p>If you suspect that labelers are inconsistent in how they’re annotating the data, it is helpful to ask two labelers to label the same example. If the first labeler annotates a defect as a chip while the second labeler annotates it as a scratch, you know there’s at least one inconsistency in your dataset. Other common inconsistencies in vision applications include bounding box size, number of bounding boxes, label names, etc. If you’re able to identify the inconsistencies and clean them up, your algorithm’s performance will significantly improve.</p><p>3. Clarify labeling instructions by tracking down ambiguous examples</p><p>When you are trying to streamline your data labeling process, identifying ambiguous examples can help you clear instructions for how to label edge cases. Your labeling instructions are your single source of truth, and the instructions should be labeled with examples of the concepts.</p><p>4. Toss out noisy examples. More data is not always better!</p><p>If you were given the 100 pill examples and asked to train the learning algorithm to detect defects on pills, you might only be confusing your learning algorithm if the data quality is so poor. Instead, if you spotted that some of the images were poorly-focused or had bad contrast, you should toss them out. Even if this leaves you with only half the training set, your algorithm will be able to more clearly detect the defect you are looking for.</p><p>Tip 5: Use error analysis to focus on subset of data to improve</p><p>Oftentimes when you’re given a dataset, there are often so many different aspects of the data that all need work, whether that be cleaning up labels, setting thresholds, capturing better data, etc. Trying to improve all these different aspects of the data all at once can be too broad and unfocused an effort. Instead, repeatedly using error analysis is critical to deciding what part of the learning algorithm’s performance is unacceptable or which you wish to improve.</p><p>More details — <a href="https://landing.ai/tips-for-a-data-centric-ai-approach/">https://landing.ai/tips-for-a-data-centric-ai-approach/</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=9a8a3b6d5641" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Human and Educational Psychology]]></title>
            <link>https://medium.com/@karimkhan.it/human-and-educational-psychology-404ae68dfe5f?source=rss-94455fbaa618------2</link>
            <guid isPermaLink="false">https://medium.com/p/404ae68dfe5f</guid>
            <category><![CDATA[psychology]]></category>
            <category><![CDATA[human-behavior]]></category>
            <category><![CDATA[mental-health]]></category>
            <dc:creator><![CDATA[Karimkhan]]></dc:creator>
            <pubDate>Thu, 06 Jan 2022 06:05:16 GMT</pubDate>
            <atom:updated>2022-01-06T06:12:51.701Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*MCI_30GVirCkiuBsJyJmvA.jpeg" /></figure><p>Hello All</p><p>Today I am starting a course on “Human and Educational Psychology”. I will share my learning with the goal of practicing.</p><blockquote>According to BF Skinner, education psychology deals with the behavior of human beings in an educational situation.</blockquote><blockquote>Trow’s describes educational psychology as a study of the psychological aspects of an educational situation.</blockquote><p>Schools of thought of our learning in this course will be following —</p><ul><li>Cognitive development</li><li>Stages of development</li><li>Motivation</li><li>Learning and Learning Experience</li><li>Emotions</li><li>Happiness</li><li>Memory and</li><li>Intelligence.</li></ul><p>Aristotle is understood to be the first psychologist. He was born in 383 B.C. He was broadly interested in the nature of living things.</p><p>He certainly used the term psyche to refer to the essence of life.</p><p>Modern psychologists study the same actions, thoughts, and feelings that fascinated Aristotle.</p><p>Indeed the term psychology comes from Aristotle&#39;s word “<strong>Psyche</strong>”</p><h4>In the modern science of psychology, psychology is defined as the science of behavior and mental process.</h4><p>It has three important terms</p><ol><li>Mental Process</li><li>Science</li><li>Behavior</li></ol><p>We will see them in detail.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=404ae68dfe5f" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Why Python and how to get started.]]></title>
            <link>https://medium.com/@karimkhan.it/why-python-and-how-to-get-started-c996a330449d?source=rss-94455fbaa618------2</link>
            <guid isPermaLink="false">https://medium.com/p/c996a330449d</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[python-programming]]></category>
            <category><![CDATA[python]]></category>
            <category><![CDATA[data-scientist]]></category>
            <dc:creator><![CDATA[Karimkhan]]></dc:creator>
            <pubDate>Tue, 08 Sep 2020 13:27:44 GMT</pubDate>
            <atom:updated>2020-09-08T13:55:08.102Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*-ljHqHHV-KzkSsHRMhRXUw.jpeg" /></figure><p><strong>Python</strong> is a great open-source, interpreted, object-oriented programming language. There is no concept of structure like <strong>C/C++ </strong>&amp;<strong> Go</strong> language. Python is a language that can be used for developing anything and everything you want.</p><p>Before we get started with Python, let me explain why it is important to learn python.</p><p><strong>Data Science: </strong>— This is one of the most and single most significant reason why many programmers are learning python. People who are interested to learn a python programming language, have a great opportunity to make a career in Data Science due to exciting work with a high pay scale.</p><p>After learning the python language you can</p><ol><li>Create scripts to automate stuff</li><li>Do data analytics</li><li>Information extraction</li><li>NLP on data</li><li>Machine learning model building</li><li>Do statistical analysis</li><li>Perform computer vision on Image and video data</li><li>Go into web development and so on</li></ol><p><strong>How to get started with Python?</strong></p><p>According to me, the most recommended source for learning python is —</p><p><a href="https://www.coursera.org/specializations/python#courses">Python for Everybody</a></p><p>This Specialization builds on the success of the Python for Everybody course and will introduce fundamental programming concepts including data structures, networked application program interfaces, and databases, using the Python programming language. In the Capstone Project, you’ll use the technologies learned throughout the Specialization to design and create your own applications for data retrieval, processing, and visualization.</p><p>If you want to focus on Data science only, in that case, Course 1, 2, are sufficient and add 5th if you want to dive into Retrieving, Processing, and Visualizing Data with Python. Here is the link</p><p>Course 1 — <a href="https://www.coursera.org/learn/python?specialization=python">https://www.coursera.org/learn/python?specialization=python</a></p><p>Course 2 — <a href="https://www.coursera.org/learn/python-data?specialization=python">https://www.coursera.org/learn/python-data?specialization=python</a></p><p>Coruse 5 — <a href="https://www.coursera.org/learn/python-data-visualization">https://www.coursera.org/learn/python-data-visualization</a></p><p>If you want to learn Python for web development and database activity</p><p>Course 3-<a href="https://www.coursera.org/learn/python-network-data?specialization=python">https://www.coursera.org/learn/python-network-data?specialization=python</a></p><p>Course 4- <a href="https://www.coursera.org/learn/python-databases?specialization=python">https://www.coursera.org/learn/python-databases?specialization=python</a></p><p><strong>If someone wants to learn python by quick examples without taking any course</strong></p><ul><li><a href="https://python3.guide/">Start learning Python</a></li><li><a href="https://www.w3schools.com/python/python_getstarted.asp">Python Getting Started</a></li></ul><p><a href="https://docs.python.org/3/tutorial/index.html">https://docs.python.org/3/tutorial/index.html</a></p><p><strong>More resources to explore</strong></p><p>Here I have listed some more resources which can help you to learn from from beginner to advanced level</p><ol><li>DataCamp Intro to Python for Data Science — <a href="https://www.datacamp.com/courses/intro-to-python-for-data-science">Intro to Python for Data Science</a></li><li><a href="https://www.dataquest.io/">Learn Python for Data Science — Dataquest</a></li><li>Collection of 53 Free Python books — <a href="http://importpython.com/books">Python Programming Books</a> [ click free. ] . Includes all the books mentioned below.</li><li><a href="http://amzn.to/1UsF4MF">Python: Learn Python in One Day and Learn It Well</a></li><li>Codecademy: <a href="https://www.codecademy.com/learn/python">Python</a></li><li><a href="https://www.udemy.com/python-step-by-step-build-a-data-analysis-program/?couponCode=quoraiw">Python Step by Step: Build a Data Analysis Program</a> (Disclosure: Added by author)</li><li><a href="http://amzn.to/1S3CrSb">Learning Python, 5th Edition</a></li><li><a href="http://amzn.to/1lVUMEh">Learn Python The Hardway</a> (<a href="http://learnpythonthehardway.org/">http://learnpythonthehardway.org/</a>)</li><li>Python: The Essential Reference (<a href="http://www.informit.com/store/product.aspx?isbn=0672329786">http://www.informit.com/store/pr...</a>)</li><li>How to Think like a Computer Scientist (<a href="http://greenteapress.com/thinkpython/thinkCSpy/">http://greenteapress.com/thinkpy...</a>)</li></ol><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=c996a330449d" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Quick and Dirty start with Data science — Part 1]]></title>
            <link>https://medium.com/@karimkhan.it/quick-and-dirty-start-with-data-science-part-1-41010f9c1197?source=rss-94455fbaa618------2</link>
            <guid isPermaLink="false">https://medium.com/p/41010f9c1197</guid>
            <category><![CDATA[python]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[nlp]]></category>
            <dc:creator><![CDATA[Karimkhan]]></dc:creator>
            <pubDate>Tue, 01 Oct 2019 06:51:16 GMT</pubDate>
            <atom:updated>2019-10-01T06:51:16.335Z</atom:updated>
            <content:encoded><![CDATA[<h3>Quick and Dirty start with Data science — Part 1</h3><p>Today many experienced and freshers want to start their career in Data Science.</p><p>Here is a quick and dirty way to get started with Data Science : )</p><p>First, you should be aware of any of these two languages which are most common for Data science and analytics</p><ol><li>Python</li><li>R</li></ol><p>I prefer Python</p><p><strong>Step 1 (3–4 Days)</strong></p><p>Few good resources to get started with Python</p><ol><li><a href="https://www.learnpython.org/">https://www.learnpython.org/</a> ( Free)</li><li><a href="https://hackr.io/tutorials/learn-python">https://hackr.io/tutorials/learn-python</a> ( You can go for paid too ) #ExtraWorkForBetterKnowledge</li></ol><p><strong>Step 2 (3 Days)</strong></p><p>Once you are good with basic python skills you can get introduced with Numpy and Pandas. This can help a lot for numerical data analysis, time series problems.</p><ol><li><a href="https://www.learnpython.org/en/Numpy_Arrays">https://www.learnpython.org/en/Numpy_Arrays</a></li><li><a href="https://www.learnpython.org/en/Pandas_Basics">https://www.learnpython.org/en/Pandas_Basics</a></li></ol><p>Once you do this much and if you have good analytics skills you can work on numerical data analysis problem</p><p><strong>Step 3 (3 Days)</strong></p><p>After completing step 1 and 2 you are familiar with Python and numerical analysis libraries. Now let&#39;s get started with text analysis.</p><p>Most of the text analytics problem require NLP and Machine learning knowledge. We will begin with basic text processing task which can help you to understand how text can be parsed, pre-processed and Information Extraction can be done. For that, I would like you to complete</p><ol><li><a href="https://www.nltk.org/book/">https://www.nltk.org/book/</a></li></ol><p>There is one more NLP library Spacy to get more knowledge about NLP, but don&#39;t want you to get confused so I am keeping it for getting more knowledge — <a href="https://spacy.io/usage/examples">https://spacy.io/usage/examples</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=41010f9c1197" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>