KindXiaoming / BIMTLinks
Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.
☆171Updated 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☆210Updated last year
- Automatic gradient descent☆208Updated 2 years ago
- Official Implementation of the ICML 2023 paper: "Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally …☆72Updated 2 years ago
- ☆222Updated 2 weeks ago
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆91Updated 4 months ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆77Updated 3 years ago
- Omnigrok: Grokking Beyond Algorithmic Data☆58Updated 2 years ago
- Tools for working with the Abstraction & Reasoning Corpus☆194Updated 11 months ago
- ☆51Updated last year
- ☆200Updated 7 months ago
- A State-Space Model with Rational Transfer Function Representation.☆79Updated last year
- σ-GPT: A New Approach to Autoregressive Models☆65Updated 11 months ago
- Learning Universal Predictors☆77Updated 11 months ago
- Graph neural networks in JAX.☆67Updated last year
- Neural Networks and the Chomsky Hierarchy☆207Updated last year
- ☆163Updated last year
- Because we don't have enough time to read everything☆89Updated 9 months ago
- Parameter-Free Optimizers for Pytorch☆130Updated last year
- A simple implimentation of Bayesian Flow Networks (BFN)☆240Updated last year
- The Energy Transformer block, in JAX☆59Updated last year
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆84Updated last year
- 🧱 Modula software package☆207Updated 3 months ago
- ☆167Updated 3 months ago
- Repository for code used in the xVal paper☆137Updated last year
- Hierarchical Associative Memory User Experience☆101Updated this week
- ☆55Updated last year
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆190Updated last year
- Meta-Learning for Compositionality (MLC) for modeling human behavior☆142Updated last year
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆183Updated 2 years ago
- Cellular Automata Accelerated in JAX (Oral at ICLR 2025)☆206Updated 2 months ago