Recurrent Neural Networks Python Packages

returnn

The RWTH extensible training framework for universal recurrent neural networks

reservoirpy

A simple and flexible code for Reservoir Computing architectures like Echo State Networks

scalecast

The practitioner's forecasting library

hrm-pytorch

Exploration into the proposed architecture from Sapient Intelligence of Singapore 🇸🇬

supernnova

Open Source Photometric classification https://supernnova.readthedocs.io

mambatransformer

Integrating Mamba/SSMs with Transformer for Enhanced Long Context and High-Quality Sequence Modeling

light-recurrent-unit-pytorch

Implementation of a Light Recurrent Unit in Pytorch

echoes

Machine Learning with Echo State Networks in Python

nnx-ppo

Implementation of PPO for recurrent/stateful networks using JAX and flax.nnx

easyesn

Python library for Reservoir Computing using Echo State Networks

nets

Recreating PyTorch from scratch, using Numpy. Supports FCN, CNN, RNN layers.

nonlincausality

Python package for Granger causality test with nonlinear forecasting methods.

pynncml

Library for rain estimation and detection built with PyTorch. This library provides an implementation of algorithms for extracting rain-rate using data from commercial microwave links (CMLs). Addinaly this project provide an example dataset with data from two CMLs and implementation of performance and robustness metrics

keras-ordered-neurons

Ordered Neurons LSTM

pytorch-adaptive-computation-time

A PyTorch implementation of adaptive computation time RNNs that's clean, idiomatic, and extensible.

keras-htr

A toolkit for training CNN-1DRNN-CTC model to perform line-level Handwritten Text Recognition

psychrnn

Easy-to-use package for the modeling and analysis of neural network dynamics, directed towards cognitive neuroscientists.

tsa-course

Book and material for the course "Time series analysis with Python" (STA-2003)

esnpy

Out-of-the-box framework for Echo State Networks

chicksexer

A Python package for gender classification.

rmdl

RMDL: Random Multimodel Deep Learning for Classification

liquidnet

Implementation of Liquid Nets in Pytorch

mdrnn

Custom Keras layers for implementing multi-dimensional recurrent neural networks (MDRNNs)

timekan

Python library designed to integrate Kolmogorov Arnold Networks with recurrent mechanisms.