KindXiaoming / BIMT
Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.
โ159Updated last year
Related projects: โ
- The boundary of neural network trainability is fractalโ155Updated 7 months ago
- Swarming algorithms like PSO, Ant Colony, Sakana, and more in PyTorch ๐โ106Updated this week
- A MAD laboratory to improve AI architecture designs ๐งชโ84Updated 4 months ago
- Generative Flow Networks - GFlowNetโ161Updated 3 weeks ago
- Omnigrok: Grokking Beyond Algorithmic Dataโ45Updated last year
- Reverse Engineering the Abstraction and Reasoning Corpusโ130Updated last month
- Learning Universal Predictorsโ67Updated last month
- A State-Space Model with Rational Transfer Function Representation.โ61Updated 4 months ago
- Official Implementation of the ICML 2023 paper: "Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally โฆโ68Updated last year
- Automatic gradient descentโ206Updated last year
- โ180Updated 2 months ago
- My writings about ARC (Abstraction and Reasoning Corpus)โ55Updated 3 weeks ago
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAXโ74Updated 7 months ago
- SR based on LLMs.โ78Updated last year
- Graph neural networks in JAX.โ66Updated 3 months ago
- Tools for working with the Abstraction & Reasoning Corpusโ137Updated last month
- โ248Updated last month
- TopoBenchmarkX is a Python library designed to standardize benchmarking and accelerate research in Topological Deep Learningโ65Updated this week
- Meta-Learning for Compositionality (MLC) for modeling human behaviorโ134Updated 8 months ago
- Domain Specific Language for the Abstraction and Reasoning Corpusโ152Updated last month
- Demonstrations of Loss of Plasticity and Implementation of Continual Backpropagationโ117Updated 3 weeks ago
- PyTorch implementation of Structured State Space for Sequence Modeling (S4), based on Annotated S4.โ61Updated 6 months ago
- โ73Updated 5 months ago
- โ104Updated last week
- โ42Updated 3 months ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"โ55Updated 2 years ago
- LoRA for arbitrary JAX models and functionsโ127Updated 6 months ago
- Tensor Network Library with Autogradโ106Updated last week
- A package for defining deep learning models using categorical algebraic expressions.โ53Updated last month
- Visualizations of the theory behind diffusion models.โ63Updated 5 months ago