KindXiaoming / BIMTLinks
Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.
☆174Updated 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☆221Updated 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 …☆77Updated 2 years ago
- ☆234Updated last month
- Hierarchical Associative Memory User Experience☆105Updated last month
- Learning Universal Predictors☆81Updated last year
- Neural Networks and the Chomsky Hierarchy☆212Updated last year
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆81Updated 3 years ago
- Omnigrok: Grokking Beyond Algorithmic Data☆62Updated 2 years ago
- Meta-Learning for Compositionality (MLC) for modeling human behavior☆145Updated last month
- ☆68Updated 9 months ago
- Graph neural networks in JAX.☆68Updated last year
- ☆230Updated last year
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆107Updated last month
- Parameter-Free Optimizers for Pytorch☆130Updated last year
- The history files when recording human interaction while solving ARC tasks☆118Updated this week
- Repository for code used in the xVal paper☆146Updated last year
- Getting crystal-like representations with harmonic loss☆194Updated 8 months ago
- A State-Space Model with Rational Transfer Function Representation.☆83Updated last year
- Tools for working with the Abstraction & Reasoning Corpus☆212Updated 4 months ago
- Because we don't have enough time to read everything☆89Updated last year
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆92Updated last year
- A simple implimentation of Bayesian Flow Networks (BFN)☆240Updated last year
- σ-GPT: A New Approach to Autoregressive Models☆70Updated last year
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆198Updated last year
- ☆211Updated 4 months ago
- Resources from the EleutherAI Math Reading Group☆54Updated 10 months ago
- Code for 1st place solution to Kaggle's Abstraction and Reasoning Challenge☆163Updated 5 months ago
- A Mechanistic Interpretability Analysis of Grokking☆23Updated 3 years ago
- ☆164Updated last year