brain.js - 🤖 Neural networks in JavaScript

•    Javascript

---

brain.js is a library of Neural Networks written in JavaScript. 💡 Note: This is a continuation of the harthur/brain repository (which is not maintained anymore). For more details, check out this issue.

neural-network brain recurrent-neural-networks easy-to-use api web nodejs browser convolutional-neural-networks node stream ai artificial-intelligence brainjs brain.js feed-forward classifier neural network neural-networks machine-learning synapse recurrent long-short-term-memory gated-recurrent-unit rnn lstm gru

theano_lstm - :microscope: Nano size Theano LSTM module

•    Python

---

Implements most of the great things that came out in 2014 concerning recurrent neural networks, and some good optimizers for these types of networks. This module also contains the SGD, AdaGrad, and AdaDelta gradient descent methods that are constructed using an objective function and a set of theano variables, and returns an updates dictionary to pass to a theano function.

machine-learning recurrent-networks theano lstm gru adadelta dropout automatic-differentiation neural-network tutorial

Hands-On-Deep-Learning-Algorithms-with-Python - Master Deep Learning Algorithms with Extensive Math by Implementing them using TensorFlow

•    Jupyter

---

Deep learning is one of the most popular domains in the artificial intelligence (AI) space, which allows you to develop multi-layered models of varying complexities. This book is designed to help you grasp things, from basic deep learning algorithms to the more advanced algorithms. The book is designed in a way that first you will understand the algorithm intuitively, once you have a basic understanding of the algorithms, then you will master the underlying math behind them effortlessly and then you will learn how to implement them using TensorFlow step by step. The book covers almost all the state of the art deep learning algorithms. First, you will get a good understanding of the fundamentals of neural networks and several variants of gradient descent algorithms. Later, you will explore RNN, Bidirectional RNN, LSTM, GRU, seq2seq, CNN, capsule nets and more. Then, you will master GAN and various types of GANs and several different autoencoders.

tensorflow word-embeddings gru autoencoder gans doc2vec skip-thoughts adagrad cyclegan deep-learning-mathematics capsule-network few-shot-learning quick-thought deep-learning-scratch nadam deep-learning-math lstm-math cnn-math rnn-derivation contractive-autonencoders

nmt-keras - Neural Machine Translation with Keras (Theano/Tensorflow)

•    Python

---

Neural Machine Translation with Keras (Theano and Tensorflow). for obtaining the required packages for running this library.

neural-machine-translation keras deep-learning sequence-to-sequence theano machine-learning nmt machine-translation lstm-networks gru tensorflow attention-mechanism web-demo transformer attention-is-all-you-need attention-model attention-seq2seq

tensorflow-lstm-sin - TensorFlow 1.3 experiment with LSTM (and GRU) RNNs for sine prediction

•    Python

---

Single- and multilayer LSTM networks with no additional output nonlinearity based on aymericdamien's TensorFlow examples and Sequence prediction using recurrent neural networks. Experiments with varying numbers of hidden units, LSTM cells and techniques like gradient clipping were conducted using static_rnn and dynamic_rnn. All networks have been optimized using Adam on the MSE loss function.

tensorflow lstm recurrent-neural-networks neural-network timeseries prediction experiment gru

rnn-theano - RNN(LSTM, GRU) in Theano with mini-batch training; character-level language models in Theano

•    Python

---

RNN(LSTM, GRU) in Theano with mini-batch training; character-level language models in Theano

rnn lstm gru language-model

tf-ran-cell - Recurrent Additive Networks for Tensorflow

•    Python

---

This is a implementation of Recurrent Additive Networks that extends Tensorflow's RNNCell.

deep-learning tensorflow rnn gru lstm

SUDL - light deep neural network tools box(LSTM,GRU,RNN,CNN,Bi-LSTM,etc)

•    C++

---

net architecture is built by proto file that you defined, just like what the examples do.

ann lstm gru deep-learning

pytorch-kaldi - pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems

•    Perl

---

pytorch-kaldi is a public repository for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit. The provided solution is designed for large-scale speech recognition experiments on both standard machines and HPC clusters.

speech-recognition gru dnn kaldi rnn-model pytorch timit deep-learning deep-neural-networks recurrent-neural-networks multilayer-perceptron-network lstm lstm-neural-networks speech asr rnn dnn-hmm

theano-kaldi-rnn - THEANO-KALDI-RNNs is a project implementing various Recurrent Neural Networks (RNNs) for RNN-HMM speech recognition

•    Perl

---

THEANO-KALDI-RNNs is a software which offers the possibility to use various Recurrent Neural Networks (RNNs) in the context of a Kaldi-based hybrid HMM/RNN speech recognizer. Note: A new project called "pytorch-kaldi" https://github.com/mravanelli/pytorch-kaldi is now available. If you are interested, please take a look into it.

recurrent-neural-networks gated-recurrent-units kaldi rnn gru timit theano theano-kaldi-rnns deep-learning deep-neural-networks

baiduyun_deeplearning_competition - 百度云魅族深度学习应用大赛

•    Jupyter

---

百度云魅族深度学习应用大赛

gru ctc-loss ocr deep-learning keras

Hierarchical-Attention-Network - Implementation of Hierarchical Attention Networks in PyTorch

•    Jupyter

---

We know that documents have a hierarchical structure, words combine to form sentences and sentences combine to form documents. We can try to learn that structure or we can input this hierarchical structure into the model and see if it improves the performance of existing models. This paper exploits that structure to build a classification model. This is a (close) implementation of the model in PyTorch.

pytorch deep-learning nlp document-classification gru word2vec hierarchical-attention-networks