<?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 Siwei Causevic on Medium]]></title>
        <description><![CDATA[Stories by Siwei Causevic on Medium]]></description>
        <link>https://medium.com/@siwei-causevic?source=rss-301dc9114da0------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*2Kg6aIETqq7G0wLHyJHGwA.jpeg</url>
            <title>Stories by Siwei Causevic on Medium</title>
            <link>https://medium.com/@siwei-causevic?source=rss-301dc9114da0------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Tue, 17 Nov 2026 14:37:36 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@siwei-causevic/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[Generalized Advantage Estimation in Reinforcement Learning]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/generalized-advantage-estimation-in-reinforcement-learning-bf4a957f7975?source=rss-301dc9114da0------2"><img src="https://cdn-images-1.medium.com/max/2600/1*D9Ns5EYuTi_H-7feGNmRFg.jpeg" width="4898"></a></p><p class="medium-feed-snippet">Bias and Variance tradeoff in Policy Gradient</p><p class="medium-feed-link"><a href="https://medium.com/data-science/generalized-advantage-estimation-in-reinforcement-learning-bf4a957f7975?source=rss-301dc9114da0------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/generalized-advantage-estimation-in-reinforcement-learning-bf4a957f7975?source=rss-301dc9114da0------2</link>
            <guid isPermaLink="false">https://medium.com/p/bf4a957f7975</guid>
            <category><![CDATA[policy-gradient]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[reinforcement-learning]]></category>
            <dc:creator><![CDATA[Siwei Causevic]]></dc:creator>
            <pubDate>Mon, 27 Mar 2023 03:18:35 GMT</pubDate>
            <atom:updated>2023-03-28T15:20:37.865Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Self-supervised Transformer Models — BERT, GPT3, MUM and PaML]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/self-supervised-transformer-models-bert-gpt3-mum-and-paml-2b5e29ea0c26?source=rss-301dc9114da0------2"><img src="https://cdn-images-1.medium.com/max/1446/1*CQaJrLWzfwcHX9E6YPQM_Q.jpeg" width="1446"></a></p><p class="medium-feed-snippet">In the early days, NLP systems are mostly rule-based that are later replaced by machine learning models. Training deep learning language&#x2026;</p><p class="medium-feed-link"><a href="https://medium.com/data-science/self-supervised-transformer-models-bert-gpt3-mum-and-paml-2b5e29ea0c26?source=rss-301dc9114da0------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/self-supervised-transformer-models-bert-gpt3-mum-and-paml-2b5e29ea0c26?source=rss-301dc9114da0------2</link>
            <guid isPermaLink="false">https://medium.com/p/2b5e29ea0c26</guid>
            <category><![CDATA[google-bard]]></category>
            <category><![CDATA[chatgpt-vs-google-bard]]></category>
            <category><![CDATA[chatgpt]]></category>
            <category><![CDATA[gpt-3]]></category>
            <category><![CDATA[large-language-models]]></category>
            <dc:creator><![CDATA[Siwei Causevic]]></dc:creator>
            <pubDate>Wed, 06 Jul 2022 02:38:07 GMT</pubDate>
            <atom:updated>2023-04-23T17:45:35.517Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Search Algorithms — Concepts and Implementation]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/search-algorithms-concepts-and-implementation-1073594aeda6?source=rss-301dc9114da0------2"><img src="https://cdn-images-1.medium.com/max/2600/1*62aJ_5U6DGqm2MKZTo_smA.jpeg" width="4032"></a></p><p class="medium-feed-snippet">A*, Dijkstra, Dynamic Programming, BFS, DFS and IDDFS</p><p class="medium-feed-link"><a href="https://medium.com/data-science/search-algorithms-concepts-and-implementation-1073594aeda6?source=rss-301dc9114da0------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/search-algorithms-concepts-and-implementation-1073594aeda6?source=rss-301dc9114da0------2</link>
            <guid isPermaLink="false">https://medium.com/p/1073594aeda6</guid>
            <category><![CDATA[dijkstra]]></category>
            <category><![CDATA[depth-first-search]]></category>
            <category><![CDATA[dynamic-programming]]></category>
            <category><![CDATA[a-star-algorithm]]></category>
            <category><![CDATA[breadth-first-search]]></category>
            <dc:creator><![CDATA[Siwei Causevic]]></dc:creator>
            <pubDate>Fri, 13 Aug 2021 03:32:52 GMT</pubDate>
            <atom:updated>2021-08-13T21:58:39.884Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Policy Gradient REINFORCE Algorithm with Baseline]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/policy-gradient-reinforce-algorithm-with-baseline-e95ace11c1c4?source=rss-301dc9114da0------2"><img src="https://cdn-images-1.medium.com/max/2600/1*Ep_th8IOf19TqTcZdKwe7Q.jpeg" width="4032"></a></p><p class="medium-feed-snippet">Algorithm and Implementation in Tensorflow</p><p class="medium-feed-link"><a href="https://medium.com/data-science/policy-gradient-reinforce-algorithm-with-baseline-e95ace11c1c4?source=rss-301dc9114da0------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/policy-gradient-reinforce-algorithm-with-baseline-e95ace11c1c4?source=rss-301dc9114da0------2</link>
            <guid isPermaLink="false">https://medium.com/p/e95ace11c1c4</guid>
            <category><![CDATA[reinforcement-learning]]></category>
            <category><![CDATA[policy-gradient]]></category>
            <category><![CDATA[tensorflow]]></category>
            <category><![CDATA[hands-on-tutorials]]></category>
            <category><![CDATA[editors-pick]]></category>
            <dc:creator><![CDATA[Siwei Causevic]]></dc:creator>
            <pubDate>Fri, 19 Mar 2021 21:41:15 GMT</pubDate>
            <atom:updated>2023-03-19T19:23:54.832Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Implement Expectation-Maximization(EM) Algorithm in Python from Scratch]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/implement-expectation-maximization-em-algorithm-in-python-from-scratch-f1278d1b9137?source=rss-301dc9114da0------2"><img src="https://cdn-images-1.medium.com/max/2600/1*0NXWjcs9VDnfh8f4uk8nOg.jpeg" width="3024"></a></p><p class="medium-feed-snippet">Unsupervised and Semi-supervised Gaussian Mixture Models (GMM)</p><p class="medium-feed-link"><a href="https://medium.com/data-science/implement-expectation-maximization-em-algorithm-in-python-from-scratch-f1278d1b9137?source=rss-301dc9114da0------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/implement-expectation-maximization-em-algorithm-in-python-from-scratch-f1278d1b9137?source=rss-301dc9114da0------2</link>
            <guid isPermaLink="false">https://medium.com/p/f1278d1b9137</guid>
            <category><![CDATA[gaussian-mixture-model]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[hands-on-tutorials]]></category>
            <category><![CDATA[editors-pick]]></category>
            <dc:creator><![CDATA[Siwei Causevic]]></dc:creator>
            <pubDate>Thu, 26 Nov 2020 18:33:12 GMT</pubDate>
            <atom:updated>2023-03-19T19:24:58.080Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Frequentist vs. Bayesian Approaches in Machine Learning]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/frequentist-vs-bayesian-approaches-in-machine-learning-86ece21e820e?source=rss-301dc9114da0------2"><img src="https://cdn-images-1.medium.com/max/2600/1*GBmsN3IkeBKhtmeAd91TTQ.jpeg" width="4032"></a></p><p class="medium-feed-snippet">A Comparison of Linear Regression and Bayesian Linear Regression</p><p class="medium-feed-link"><a href="https://medium.com/data-science/frequentist-vs-bayesian-approaches-in-machine-learning-86ece21e820e?source=rss-301dc9114da0------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/frequentist-vs-bayesian-approaches-in-machine-learning-86ece21e820e?source=rss-301dc9114da0------2</link>
            <guid isPermaLink="false">https://medium.com/p/86ece21e820e</guid>
            <category><![CDATA[bayesian-machine-learning]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[editors-pick]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[bayesian-statistics]]></category>
            <dc:creator><![CDATA[Siwei Causevic]]></dc:creator>
            <pubDate>Thu, 27 Aug 2020 17:09:12 GMT</pubDate>
            <atom:updated>2020-08-30T17:43:44.378Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[A Structural Overview of Reinforcement Learning Algorithms]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/an-overview-of-classic-reinforcement-learning-algorithms-part-1-f79c8b87e5af?source=rss-301dc9114da0------2"><img src="https://cdn-images-1.medium.com/max/2600/1*KEiw2brFVLsCZSNMegXVzw.jpeg" width="4032"></a></p><p class="medium-feed-snippet">Actor Critic, Policy Gradient, DQN, VFA, TD Learning, Model-based and Model-free Monte Carlo, Dynamic Programming</p><p class="medium-feed-link"><a href="https://medium.com/data-science/an-overview-of-classic-reinforcement-learning-algorithms-part-1-f79c8b87e5af?source=rss-301dc9114da0------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/an-overview-of-classic-reinforcement-learning-algorithms-part-1-f79c8b87e5af?source=rss-301dc9114da0------2</link>
            <guid isPermaLink="false">https://medium.com/p/f79c8b87e5af</guid>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[towards-data-science]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[reinforcement-learning]]></category>
            <category><![CDATA[markov-decision-process]]></category>
            <dc:creator><![CDATA[Siwei Causevic]]></dc:creator>
            <pubDate>Thu, 18 Jun 2020 02:37:33 GMT</pubDate>
            <atom:updated>2021-08-13T18:53:52.503Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Generative vs Discriminative Probabilistic Graphical Models]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/generative-vs-2528de43a836?source=rss-301dc9114da0------2"><img src="https://cdn-images-1.medium.com/max/1838/0*X_WtXb2MJMqgGdC1" width="1838"></a></p><p class="medium-feed-snippet">A Comparison of Naive Bayes and Logistic Regression</p><p class="medium-feed-link"><a href="https://medium.com/data-science/generative-vs-2528de43a836?source=rss-301dc9114da0------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/generative-vs-2528de43a836?source=rss-301dc9114da0------2</link>
            <guid isPermaLink="false">https://medium.com/p/2528de43a836</guid>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[probabilistic-graphical]]></category>
            <category><![CDATA[naive-bayes]]></category>
            <category><![CDATA[logistic-regression]]></category>
            <dc:creator><![CDATA[Siwei Causevic]]></dc:creator>
            <pubDate>Sun, 05 Apr 2020 02:50:46 GMT</pubDate>
            <atom:updated>2021-08-13T18:53:57.510Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Image Denoising with Gibbs Sampling (MCMC)]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/image-denoising-with-gibbs-sampling-mcmc-concepts-and-code-implementation-11d42a90e153?source=rss-301dc9114da0------2"><img src="https://cdn-images-1.medium.com/max/1838/0*RBAn0XpIqeH-yud-" width="1838"></a></p><p class="medium-feed-snippet">Concepts and Code Implementation</p><p class="medium-feed-link"><a href="https://medium.com/data-science/image-denoising-with-gibbs-sampling-mcmc-concepts-and-code-implementation-11d42a90e153?source=rss-301dc9114da0------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/image-denoising-with-gibbs-sampling-mcmc-concepts-and-code-implementation-11d42a90e153?source=rss-301dc9114da0------2</link>
            <guid isPermaLink="false">https://medium.com/p/11d42a90e153</guid>
            <category><![CDATA[image-processing]]></category>
            <category><![CDATA[gibbs-sampling]]></category>
            <category><![CDATA[markov-chain-monte-carlo]]></category>
            <dc:creator><![CDATA[Siwei Causevic]]></dc:creator>
            <pubDate>Mon, 30 Mar 2020 02:24:58 GMT</pubDate>
            <atom:updated>2021-08-13T18:54:03.139Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Deep Reinforcement Learning: Build a Deep Q-network(DQN) with TensorFlow 2 and Gym to Play CartPole]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/deep-reinforcement-learning-build-a-deep-q-network-dqn-to-play-cartpole-with-tensorflow-2-and-gym-8e105744b998?source=rss-301dc9114da0------2"><img src="https://cdn-images-1.medium.com/max/1838/0*I83aE2Gah4C7UeWE" width="1838"></a></p><p class="medium-feed-link"><a href="https://medium.com/data-science/deep-reinforcement-learning-build-a-deep-q-network-dqn-to-play-cartpole-with-tensorflow-2-and-gym-8e105744b998?source=rss-301dc9114da0------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/deep-reinforcement-learning-build-a-deep-q-network-dqn-to-play-cartpole-with-tensorflow-2-and-gym-8e105744b998?source=rss-301dc9114da0------2</link>
            <guid isPermaLink="false">https://medium.com/p/8e105744b998</guid>
            <category><![CDATA[tensorflow2]]></category>
            <category><![CDATA[dqn]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[reinforcement-learning]]></category>
            <category><![CDATA[openai-gym]]></category>
            <dc:creator><![CDATA[Siwei Causevic]]></dc:creator>
            <pubDate>Mon, 16 Dec 2019 01:29:13 GMT</pubDate>
            <atom:updated>2023-03-19T19:25:54.996Z</atom:updated>
        </item>
    </channel>
</rss>