PinnedInTDS ArchivebySiwei Causevic·Aug 27, 2020Frequentist vs. Bayesian Approaches in Machine LearningA Comparison of Linear Regression and Bayesian Linear RegressionA response icon1A response icon1
InTDS ArchivebySiwei Causevic·Mar 27, 2023Generalized Advantage Estimation in Reinforcement LearningBias and Variance tradeoff in Policy Gradient
InTDS ArchivebySiwei Causevic·Jul 6, 2022Self-supervised Transformer Models — BERT, GPT3, MUM and PaMLIn the early days, NLP systems are mostly rule-based that are later replaced by machine learning models. Training deep learning language…A response icon2A response icon2
InTDS ArchivebySiwei Causevic·Aug 13, 2021Search Algorithms — Concepts and ImplementationA*, Dijkstra, Dynamic Programming, BFS, DFS and IDDFS
InTDS ArchivebySiwei Causevic·Mar 19, 2021Policy Gradient REINFORCE Algorithm with BaselineAlgorithm and Implementation in TensorflowA response icon2A response icon2
InTDS ArchivebySiwei Causevic·Nov 26, 2020Implement Expectation-Maximization(EM) Algorithm in Python from ScratchUnsupervised and Semi-supervised Gaussian Mixture Models (GMM)A response icon6A response icon6
InTDS ArchivebySiwei Causevic·Jun 18, 2020A Structural Overview of Reinforcement Learning AlgorithmsActor Critic, Policy Gradient, DQN, VFA, TD Learning, Model-based and Model-free Monte Carlo, Dynamic ProgrammingA response icon3A response icon3
InTDS ArchivebySiwei Causevic·Apr 5, 2020Generative vs Discriminative Probabilistic Graphical ModelsA Comparison of Naive Bayes and Logistic RegressionA response icon2A response icon2
InTDS ArchivebySiwei Causevic·Mar 30, 2020Image Denoising with Gibbs Sampling (MCMC)Concepts and Code ImplementationA response icon6A response icon6
InTDS ArchivebySiwei Causevic·Dec 16, 2019Deep Reinforcement Learning: Build a Deep Q-network(DQN) with TensorFlow 2 and Gym to Play CartPoleA response icon11A response icon11