InTDS ArchivebyThomas Kurbiel·Jan 31, 2025The Animated Monte-Carlo Tree Search (MCTS)The algorithm at the heart of AlphaGo, AlphaGo Zero, AlphaZero and MuZeroA response icon2A response icon2
InTDS ArchivebyThomas Kurbiel·Oct 12, 2021Spatial Transformer Networks — BackpropagationA Self-Contained IntroductionA response icon1A response icon1
InTDS ArchivebyThomas Kurbiel·Sep 13, 2021Spatial Transformer Networks Tutorial, Part 2 — Bilinear InterpolationA Self-Contained Introduction
InTDS ArchivebyThomas Kurbiel·Aug 30, 2021Spatial Transformer Tutorial, Part 1 — Forward and Reverse MappingA Self-Contained Introduction
InTDS ArchivebyThomas Kurbiel·Apr 28, 2021Transformer Networks: A mathematical explanation why scaling the dot products leads to more stable…How a small detail can make a huge differenceA response icon5A response icon5
InTDS ArchivebyThomas Kurbiel·Apr 22, 2021Derivative of the Softmax Function and the Categorical Cross-Entropy LossA simple and quick derivationA response icon16A response icon16
InTDS ArchivebyThomas Kurbiel·Dec 20, 2020Aleatory Overfitting vs. Epistemic OverfittingApproaching the two reasons why your model is not able to generalize wellA response icon1A response icon1
InTDS ArchivebyThomas Kurbiel·Nov 23, 2020Deriving the Backpropagation Equations from Scratch (Part 2)Gaining more insight into how neural networks are trainedA response icon5A response icon5
InTDS ArchivebyThomas Kurbiel·Nov 15, 2020Drawing the Transformer Network from Scratch (Part 1)Getting a mental model of the Transformer in a playful wayA response icon7A response icon7
