Tycho van der Ouderaa

PacmanDQN. Deep Reinforcement Learning in Pac-man

MovingMNIST. Moving MNIST as PyTorch Dataset

RevGAN. RevGAN implementation in PyTorch. We extend the Pix2pix and CycleGAN framework by exploring approximately invertible architectures in 2D and 3D. These architectures are approximately invertible by design and thus partially satisfy cycle-consistency before training even begins. Furthermore, since invertible architectures have constant memory complexity in depth, these models can be built arbitrarily deep without requiring additional memory. In the paper we demonstrate superior quantitative output on the Cityscapes and Maps datasets at near constant memory budget.

lila. Code for "Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations"

noethers-razor. Code for NeurIPS 2024 paper: "Noether's razor: Learning Conserved Quantities" by Tycho F. A. van der Ouderaa, Mark van der Wilk, Pim de Haan.

ella. Python

Char-RNN-Understanding. Understanding Character-level RNN Language Models with Diagnostic Classifiers in PyTorch.

InvertibleLanguageModel. Stacked RNN Language Model with invertible recurrent blocks

Geo-Vec. Implementation of the Geo-Vec model for embedding documents

nodejs_multiplayergame. Multiplayer game in javascript using websockets and node.js