KindXiaoming / BIMT
Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.
☆159Updated last year
Related projects: ⓘ
- The boundary of neural network trainability is fractal☆155Updated 7 months ago
- Swarming algorithms like PSO, Ant Colony, Sakana, and more in PyTorch 😊☆106Updated this week
- A MAD laboratory to improve AI architecture designs 🧪☆84Updated 4 months ago
- Generative Flow Networks - GFlowNet☆161Updated 3 weeks ago
- Omnigrok: Grokking Beyond Algorithmic Data☆45Updated last year
- Reverse Engineering the Abstraction and Reasoning Corpus☆130Updated last month
- Learning Universal Predictors☆67Updated last month
- A State-Space Model with Rational Transfer Function Representation.☆61Updated 4 months ago
- Official Implementation of the ICML 2023 paper: "Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally …☆68Updated last year
- Automatic gradient descent☆206Updated last year
- ☆180Updated 2 months ago
- My writings about ARC (Abstraction and Reasoning Corpus)☆55Updated 3 weeks ago
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆74Updated 7 months ago
- SR based on LLMs.☆78Updated last year
- Graph neural networks in JAX.☆66Updated 3 months ago
- Tools for working with the Abstraction & Reasoning Corpus☆137Updated last month
- ☆248Updated last month
- TopoBenchmarkX is a Python library designed to standardize benchmarking and accelerate research in Topological Deep Learning☆65Updated this week
- Meta-Learning for Compositionality (MLC) for modeling human behavior☆134Updated 8 months ago
- Domain Specific Language for the Abstraction and Reasoning Corpus☆152Updated last month
- Demonstrations of Loss of Plasticity and Implementation of Continual Backpropagation☆117Updated 3 weeks ago
- PyTorch implementation of Structured State Space for Sequence Modeling (S4), based on Annotated S4.☆61Updated 6 months ago
- ☆73Updated 5 months ago
- ☆104Updated last week
- ☆42Updated 3 months ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆55Updated 2 years ago
- LoRA for arbitrary JAX models and functions☆127Updated 6 months ago
- Tensor Network Library with Autograd☆106Updated last week
- A package for defining deep learning models using categorical algebraic expressions.☆53Updated last month
- Visualizations of the theory behind diffusion models.☆63Updated 5 months ago