Posts related to my YouTube videos

Variational Graph Autoencoder implemented using Jax & Jraph

Oxford MSc thesis. variational autoencoder combined with graph convolutional networks for learning locally-aware spatial prior distributions

Simplified, reproducible reimplementation of DeepMind's GraphCast weather model using graph neural networks (JAX · Haiku · Jraph). Runs on a single GPU, with honest negative-results reporting and detailed failure-mode analysis of a heavily scaled-down forecasting model.

Molecular active learning with JAX

Reinforcement Learning (RL) environments for a range of graph problems. Written in Jraph.