Felix-Petersen / difflogic
A Library for Differentiable Logic Gate Networks
☆622Updated 11 months ago
Alternatives and similar repositories for difflogic:
Users that are interested in difflogic are comparing it to the libraries listed below
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆205Updated this week
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆204Updated last year
- Annotated version of the Mamba paper☆473Updated 11 months ago
- FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores☆296Updated last month
- Forward Pass Learning and Inference Library, for neural networks and general intelligence, Signal Propagation (sigprop)☆50Updated last year
- Reimplementation of Geoffrey Hinton's Forward-Forward Algorithm☆142Updated last year
- Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"☆417Updated 2 months ago
- A repository for log-time feedforward networks☆219Updated 10 months ago
- A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.☆702Updated 9 months ago
- For optimization algorithm research and development.☆491Updated this week
- Differentiable Algorithms and Algorithmic Supervision.☆112Updated last year
- Integral Neural Networks in PyTorch☆126Updated 2 months ago
- Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"☆477Updated last year
- Code for our NeurIPS 2022 paper☆366Updated 2 years ago
- MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…☆364Updated last week
- Tensors, for human consumption☆1,183Updated 3 months ago
- Implementation of https://srush.github.io/annotated-s4☆483Updated 2 years ago
- ☆764Updated last month
- Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.☆164Updated last year
- ☆218Updated last week
- A library to inspect and extract intermediate layers of PyTorch models.☆471Updated 2 years ago
- The AdEMAMix Optimizer: Better, Faster, Older.☆177Updated 5 months ago
- torchview: visualize pytorch models☆872Updated last week
- The boundary of neural network trainability is fractal☆194Updated last year
- Kolmogorov-Arnold Networks (KAN) using Chebyshev polynomials instead of B-splines.☆363Updated 9 months ago
- Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"☆541Updated 7 months ago
- Code release for "Dropout Reduces Underfitting"☆312Updated last year
- ☆280Updated last month
- FastKAN: Very Fast Implementation of Kolmogorov-Arnold Networks (KAN)☆382Updated 8 months ago
- Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation☆1,460Updated last year