Implementing Recurrent Neural Network from Scratch

Keras implementations of three language models: character-level RNN, word-level RNN and Sentence VAE (Bowman, Vilnis et al 2016).

Implementation of Music Generation in PyTorch

Imageboard bot with recurrent neural network (RNN, GRU)

RNN-based language models in pytorch

Char RNN Language Model based on Tensorflow

BlackOut and Adaptive Softmax for language models by Chainer

The main task of the character-level language model is to predict the next character given all previous characters in a sequence of data, i.e. generates text character by character.

attempt at implementing "Memory Architectures in Recurrent Neural Network Language Models" as a part of the ICLR 2018 reproducibility challenge

s-atmech is an independent Open Source, Deep Learning python library which implements attention mechanism as a RNN(Recurrent Neural Network) Layer as Encoder-Decoder system. (Supports all Models both Luong and Bhanadau).

Code and scripts for training, testing and sampling auto-regressive recurrent language models on PyTorch with RNN, GRU and LSTM layers

Classifies the movie reviews as positive or negative using LSTM Networks

s-atmech is an independent Open Source, Deep Learning python library which implements attention mechanism as a RNN(Recurrent Neural Network) Layer as Encoder-Decoder system. (only supports Bahdanau Attention right now).

TV Script Generation with RNN with Udacity

Telugu OCR using RNN

Time series regression models

Classifying whether a disaster tweet is real or not using LSTM and GloVe word embeddings

Character Encoding RNN

In this kaggle competition I used TimeDistributed layer of keras to classify if questions asked on quora are same or duplicate.