recurrent-networks

A curated list of awesome Deep Learning tutorials, projects and communities.

Projects and exercises for the latest Deep Learning ND program https://www.udacity.com/course/deep-learning-nanodegree--nd101

Differentiable architecture search for convolutional and recurrent networks

Self-contained Machine Learning and Natural Language Processing library in Go

Implementing Recurrent Neural Network from Scratch

A Python toolkit for Reservoir Computing and Echo State Network experimentation based on pyTorch. EchoTorch is the only Python module available to easily create Deep Reservoir Computing models.

🔬 Nano size Theano LSTM module

Multi dimensional LSTM as described in Alex Graves' Paper https://arxiv.org/pdf/0705.2011.pdf

Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences (NIPS 2016) - Tensorflow 1.0

Accelerated tensor operations and dynamic neural networks based on reverse mode automatic differentiation for every device that can run Swift - from watchOS to Linux

Implementation of the paper Recurrent Independent Mechanisms (https://arxiv.org/pdf/1909.10893.pdf)

Music genre classification model using CRNN

Implementation/simulation of the predictive forward-forward credit assignment algorithm for training neurobiologically-plausible recurrent neural network models.

Implementation/simulation of the predictive forward-forward credit assignment algorithm for training neurobiologically-plausible recurrent neural network models.

Implementation of Griffin from the paper: "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"

Implementation of Griffin from the paper: "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"

A simpler Pytorch + Zeta Implementation of the paper: "SiMBA: Simplified Mamba-based Architecture for Vision and Multivariate Time series"

A simpler Pytorch + Zeta Implementation of the paper: "SiMBA: Simplified Mamba-based Architecture for Vision and Multivariate Time series"

A comprehensive collection of 35+ recurrent neural network layers for Flux.jl

A comprehensive collection of 35+ recurrent neural network layers for Flux.jl