How do neural networks learn to learn and compute?
hypernetwork-attention. Official code for the paper "Attention as a Hypernetwork"
58equilibrium-propagation. Fully documented Pytorch implementation of the Equilibrium Propagation algorithm.
42jax-hypernetwork. A simple hypernetwork implementation in jax using haiku.
24metax. flexible meta-learning in jax
16scale-compositionality. Official code for the paper Scale leads to compositional generalization.
13contrastive-meta-learning. Code accompanying the paper "A contrastive rule for meta-learning"
13modular-hyperteacher. Code accompanying the paper Discovering modular solutions that generalize compositionally
11autofsdp. Fully-sharded data parallelism (FSDP) in jax with minimal code changes.
7sparsely-gated-linear. Official code for the paper "Sparsely gated tiny linear experts"
7flaxify. Convert haiku modules to flax
4shrink-perturb. Optax implementation of shrink and perturb (Ash & Adams, 2020).
4git-workshop. Git Workshop at Frankfurt Open Science Initiative
4minimal-hypernetwork. Minimal hypernetwork implementation.
3presynaptic-stochasticity. Presynaptic Stochasticity Improves Energy Efficiency and Alleviates the Stability-Plasticity Dilemma
2llm-humanness. Are they human? Detecting large language models by probing human memory constraints
2jax-meta-learning. A collection of meta-learning algorithms in Jax
2cryptography-workshop. Cryptography Workshop for hebbian.ch
1rotation-trick-jax. JAX implementation of rotation trick
1