KindXiaoming / BIMT
Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.
☆162Updated last year
Related projects ⓘ
Alternatives and complementary repositories for BIMT
- Official Implementation of the ICML 2023 paper: "Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally …☆69Updated last year
- Omnigrok: Grokking Beyond Algorithmic Data☆49Updated last year
- σ-GPT: A New Approach to Autoregressive Models☆59Updated 3 months ago
- A State-Space Model with Rational Transfer Function Representation.☆70Updated 6 months ago
- The boundary of neural network trainability is fractal☆161Updated 9 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆95Updated 6 months ago
- ☆171Updated last year
- TopoBenchmark is a Python library designed to standardize benchmarking and accelerate research in Topological Deep Learning☆85Updated this week
- Automatic gradient descent☆206Updated last year
- Graph neural networks in JAX.☆67Updated 5 months ago
- Bootstrapping ARC☆63Updated this week
- ☆105Updated 2 weeks ago
- ☆128Updated this week
- Reverse Engineering the Abstraction and Reasoning Corpus☆196Updated last month
- Neural Networks and the Chomsky Hierarchy☆187Updated 7 months ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆63Updated 2 years ago
- Understand and test language model architectures on synthetic tasks.☆162Updated 6 months ago
- Pytorch-like dataloaders in JAX.☆59Updated last month
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆79Updated 9 months ago
- PyTorch implementation of Structured State Space for Sequence Modeling (S4), based on Annotated S4.☆70Updated 8 months ago
- Swarming algorithms like PSO, Ant Colony, Sakana, and more in PyTorch 😊☆111Updated last week
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆178Updated 5 months ago
- The history files when recording human interaction while solving ARC tasks☆95Updated this week
- A package for defining deep learning models using categorical algebraic expressions.☆56Updated 3 months ago
- The Energy Transformer block, in JAX☆53Updated 11 months ago
- Tools for working with the Abstraction & Reasoning Corpus☆159Updated 3 months ago
- SR based on LLMs.☆86Updated 2 years ago
- ☆161Updated last year
- This repository contains the code for the paper "Inferring Neural Activity Before Plasticity: A Foundation for Learning Beyond Backpropag…☆80Updated 10 months ago
- Flow-matching algorithms in JAX☆77Updated 3 months ago