Command and Conquer: Red Alert

Thermodynamic Hypergraphical Model Library in JAX

Raspberry Pi guitar pedal using neural networks to emulate real amps and effects.

Neural network emulator for guitar amplifiers.

JAX-Toolbox

Flax Image Models - State-of-the-art pre-trained vision backbones for Flax.

Implementation of numerous Vision Transformers in Google's JAX and Flax.

Pretrained deep learning models for Jax/Flax: StyleGAN2, GPT2, VGG, ResNet, etc.

📈 The package allows you to check the similarity between two shapes/curves, using Frechet distance together with Procrustes analysis.

Soft-DTW loss in JAX

Soft-DTW and Soft-DTW Divergence in Jax

An implementation of soft-DTW divergences.

The boundary of neural network trainability is fractal

Real-time Web Dashboard for Optuna.

Soft-DTW implementation in JAX with custom gradient

Experiments with simplified fast causal attention

Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai

Time series forecasting with machine learning models

A python package for time series forecasting with scikit-learn estimators.

An implementation of SoftDTW and DTW in Jax

DTW (Dynamic Time Warping) python module

Flax is a neural network library for JAX that is designed for flexibility.

Some experiments with linear RNNs with MLPs interleaved.

Non official implementation of the Linear Recurrent Unit (LRU, Orvieto et al. 2023)

Really Fast End-to-End Jax RL Implementations

A Python package for probabilistic state space modeling with JAX

The accompanying code for "Simplifying and Understanding State Space Models with Diagonal Linear RNNs" (Ankit Gupta, Harsh Mehta, Jonathan Berant).

Structured state space sequence models