KindXiaoming / BIMTLinks
Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.
☆173Updated 2 years ago
Alternatives and similar repositories for BIMT
Users that are interested in BIMT are comparing it to the libraries listed below
Sorting:
- The boundary of neural network trainability is fractal☆220Updated last year
- Automatic gradient descent☆215Updated 2 years ago
- Official Implementation of the ICML 2023 paper: "Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally …☆76Updated 2 years ago
- Learning Universal Predictors☆81Updated last year
- ☆230Updated last week
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆105Updated last month
- ☆164Updated last year
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆79Updated 3 years ago
- Omnigrok: Grokking Beyond Algorithmic Data☆62Updated 2 years ago
- Hierarchical Associative Memory User Experience☆104Updated last week
- The Energy Transformer block, in JAX☆61Updated last year
- Graph neural networks in JAX.☆68Updated last year
- ☆53Updated last year
- Cellular Automata Accelerated in JAX (Oral at ICLR 2025)☆230Updated last week
- Tools for working with the Abstraction & Reasoning Corpus☆211Updated 2 months ago
- A State-Space Model with Rational Transfer Function Representation.☆83Updated last year
- Neural Networks and the Chomsky Hierarchy☆211Updated last year
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆89Updated last year
- The history files when recording human interaction while solving ARC tasks☆118Updated last week
- Running Jax in PyTorch Lightning☆114Updated 11 months ago
- A Jax-based library for building transformers, includes implementations of GPT, Gemma, LlaMa, Mixtral, Whisper, SWin, ViT and more.☆297Updated last year
- Getting crystal-like representations with harmonic loss☆192Updated 7 months ago
- ☆200Updated 3 months ago
- ☆223Updated 11 months ago
- Official repository for the paper "A Modern Self-Referential Weight Matrix That Learns to Modify Itself" (ICML 2022 & NeurIPS 2021 Deep R…☆171Updated 5 months ago
- ☆41Updated 3 years ago
- Repository for code used in the xVal paper☆144Updated last year
- Code for 1st place solution to Kaggle's Abstraction and Reasoning Challenge☆163Updated 4 months ago
- ☆192Updated 4 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆130Updated 3 years ago