PinnedTan Pengshi AlvininTowards AITransfer Learning and Convolutional Neural Networks (CNN) — Complete GuideA complete guide from CNN to Transfer Learning, with application on Kaggle’s Cat versus Dog datasetSep 11, 20221Sep 11, 20221
PinnedTan Pengshi AlvininTowards Data ScienceThe Complete Guide to Effective Learning in Artificial IntelligenceA fundamental and complete guide to skyrocket your growth in Artificial Intelligence (or really in any subject)Oct 31, 2021Oct 31, 2021
Tan Pengshi AlvininTowards AIGraph Neural Networks (GNN) — Concepts and ApplicationsExploring the concept and applications of Graphs, and how to apply Neural Networks to itMay 23May 23
Tan Pengshi AlvininTowards AIDemystifying the Receiver Operating Characteristic (ROC) CurveInterpreting the metrics behind a supervised classification model, in particular, the ROC curve and AUCApr 223Apr 223
Tan Pengshi AlvininTowards AIReinforcement Learning: Multi-Agent Cooperation with MADQN— Part 5Multi-agent reinforcement learning with 3 MADQN frameworks on the ma-gym’s “Switch4” environmentDec 24, 2023Dec 24, 2023
Tan Pengshi AlvininILLUMINATIONProposing the Singapore River as UNESCO World Heritage SiteConsideration of factors and background in qualification for UNESCO World Heritage statusOct 19, 2023Oct 19, 2023
Tan Pengshi AlvininTowards AIReinforcement Learning: Function Approximation and Deep Q-Networks — Part 4Reinforcement Learning with continuous state spaces and gradient descent techniquesOct 2, 2023Oct 2, 2023
Tan Pengshi AlvininTowards AIReinforcement Learning: SARSA and Q-Learning — Part 3Introducing the Temporal Difference family of iterative techniques to solve the Markov Decision ProcessSep 6, 2023Sep 6, 2023
Tan Pengshi AlvininTowards AIReinforcement Learning: Dynamic Programming and Monte Carlo — Part 2Introducing two simple iterative techniques to solve the Markov Decision ProcessSep 1, 2023Sep 1, 2023
Tan Pengshi AlvininTowards AIReinforcement Learning: Markov Decision Process — Part 1Introducing the backbone of Reinforcement Learning — The Markov Decision ProcessAug 29, 20232Aug 29, 20232