Sohl-Dickstein / fractalLinks
The boundary of neural network trainability is fractal
☆218Updated last year
Alternatives and similar repositories for fractal
Users that are interested in fractal are comparing it to the libraries listed below
Sorting:
- Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.☆173Updated 2 years ago
- ☆150Updated last year
- Minimal GPT (~350 lines with a simple task to test it)☆62Updated 9 months ago
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆303Updated 2 months ago
- ☆215Updated 10 months ago
- 🧱 Modula software package☆277Updated last month
- Official Implementation of the ICML 2023 paper: "Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally …☆74Updated 2 years ago
- Getting crystal-like representations with harmonic loss☆194Updated 6 months ago
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆98Updated 6 months ago
- ☆281Updated last year
- A simple implimentation of Bayesian Flow Networks (BFN)☆240Updated last year
- Automatic gradient descent☆211Updated 2 years ago
- Parameter-Free Optimizers for Pytorch☆130Updated last year
- Deep Learning, an Energy Approach☆214Updated 3 months ago
- A 1D analogue of the MNIST dataset for measuring spatial biases and answering Science of Deep Learning questions.☆229Updated 11 months ago
- Compositional Linear Algebra☆492Updated 2 months ago
- For optimization algorithm research and development.☆539Updated last week
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆183Updated last week
- Code for the book "The Elements of Differentiable Programming".☆269Updated 3 months ago
- σ-GPT: A New Approach to Autoregressive Models☆68Updated last year
- Brain-like variational inference☆58Updated 4 months ago
- Uncertainty quantification with PyTorch☆372Updated last week
- Tools for working with the Abstraction & Reasoning Corpus☆208Updated last month
- ☆52Updated last year
- MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…☆399Updated this week
- An interactive exploration of Transformer programming.☆269Updated last year
- Neural Networks and the Chomsky Hierarchy☆209Updated last year
- Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"☆563Updated last year
- The AdEMAMix Optimizer: Better, Faster, Older.☆186Updated last year
- Resources from the EleutherAI Math Reading Group☆54Updated 7 months ago