Rnn ctcRecurrent Neural Network and Long Short Term Memory (LSTM) with Connectionist Temporal Classification implemented in Theano. Includes a Toy training example.
Stars: ✭ 220 (+158.82%)
Practical rlA course in reinforcement learning in the wild
Stars: ✭ 4,741 (+5477.65%)
Iris PythonCollection of iris classifcation program for teaching purpose
Stars: ✭ 33 (-61.18%)
AgentnetDeep Reinforcement Learning library for humans
Stars: ✭ 298 (+250.59%)
TarsA deep generative model library in Theano and Lasagne
Stars: ✭ 61 (-28.24%)
Feel The KernGenerating proportional fonts with deep learning
Stars: ✭ 59 (-30.59%)
Lstm Ctc Ocrusing rnn (lstm or gru) and ctc to convert line image into text, based on torch7 and warp-ctc
Stars: ✭ 70 (-17.65%)
Punctuator2A bidirectional recurrent neural network model with attention mechanism for restoring missing punctuation in unsegmented text
Stars: ✭ 483 (+468.24%)
CtcwordbeamsearchConnectionist Temporal Classification (CTC) decoder with dictionary and language model for TensorFlow.
Stars: ✭ 398 (+368.24%)
Repo 2016R, Python and Mathematica Codes in Machine Learning, Deep Learning, Artificial Intelligence, NLP and Geolocation
Stars: ✭ 103 (+21.18%)
Deep Learning PythonIntro to Deep Learning, including recurrent, convolution, and feed forward neural networks.
Stars: ✭ 94 (+10.59%)
Practical dlDL course co-developed by YSDA, HSE and Skoltech
Stars: ✭ 1,006 (+1083.53%)
STORN-kerasThis is a STORN (Stochastical Recurrent Neural Network) implementation for keras!
Stars: ✭ 23 (-72.94%)
DeepoSetup and customize deep learning environment in seconds.
Stars: ✭ 6,145 (+7129.41%)
SymJAXDocumentation:
Stars: ✭ 103 (+21.18%)
Theano Kaldi RnnTHEANO-KALDI-RNNs is a project implementing various Recurrent Neural Networks (RNNs) for RNN-HMM speech recognition. The Theano Code is coupled with the Kaldi decoder.
Stars: ✭ 31 (-63.53%)
sequence-rnn-pySequence analyzing using Recurrent Neural Networks (RNN) based on Keras
Stars: ✭ 28 (-67.06%)
ParrotRNN-based generative models for speech.
Stars: ✭ 601 (+607.06%)
Alphazero gomokuAn implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)
Stars: ✭ 2,570 (+2923.53%)
ReturnnThe RWTH extensible training framework for universal recurrent neural networks
Stars: ✭ 290 (+241.18%)
CtcdecoderConnectionist Temporal Classification (CTC) decoding algorithms: best path, prefix search, beam search and token passing. Implemented in Python.
Stars: ✭ 529 (+522.35%)
Machine Learning Curriculum💻 Make machines learn so that you don't have to struggle to program them; The ultimate list
Stars: ✭ 761 (+795.29%)
PsganPeriodic Spatial Generative Adversarial Networks
Stars: ✭ 108 (+27.06%)
svae cf[ WSDM '19 ] Sequential Variational Autoencoders for Collaborative Filtering
Stars: ✭ 38 (-55.29%)
SynThaiThai Word Segmentation and Part-of-Speech Tagging with Deep Learning
Stars: ✭ 41 (-51.76%)
LSTM-footballMatchWinnerThis repository contains the code for a conference paper "Predicting the football match winner using LSTM model of Recurrent Neural Networks" that we wrote
Stars: ✭ 44 (-48.24%)
DandelionA light weight deep learning framework, on top of Theano, offering better balance between flexibility and abstraction
Stars: ✭ 15 (-82.35%)
TF-Speech-Recognition-Challenge-SolutionSource code of the model used in Tensorflow Speech Recognition Challenge (https://www.kaggle.com/c/tensorflow-speech-recognition-challenge). The solution ranked in top 5% in private leaderboard.
Stars: ✭ 58 (-31.76%)
NolearnCombines the ease of use of scikit-learn with the power of Theano/Lasagne
Stars: ✭ 940 (+1005.88%)
Seq2Seq-chatbotTensorFlow Implementation of Twitter Chatbot
Stars: ✭ 18 (-78.82%)
email-summarizationA module for E-mail Summarization which uses clustering of skip-thought sentence embeddings.
Stars: ✭ 81 (-4.71%)
Multimodal-Gesture-Recognition-with-LSTMs-and-CTCAn end-to-end system that performs temporal recognition of gesture sequences using speech and skeletal input. The model combines three networks with a CTC output layer that recognises gestures from continuous stream.
Stars: ✭ 25 (-70.59%)
CapsnetCapsNet (Capsules Net) in Geoffrey E Hinton paper "Dynamic Routing Between Capsules" - State Of the Art
Stars: ✭ 423 (+397.65%)
DARNNA Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
Stars: ✭ 90 (+5.88%)
reasoning attentionUnofficial implementation algorithms of attention models on SNLI dataset
Stars: ✭ 34 (-60%)
Theano-MPIMPI Parallel framework for training deep learning models built in Theano
Stars: ✭ 55 (-35.29%)
SemiDenseNetRepository containing the code of one of the networks that we employed in the iSEG Grand MICCAI Challenge 2017, infant brain segmentation.
Stars: ✭ 55 (-35.29%)
danifojo-2018-repeatrnnComparing Fixed and Adaptive Computation Time for Recurrent Neural Networks
Stars: ✭ 32 (-62.35%)
ghiaseddinAuthor's implementation of the paper "Deep Relative Attributes" (ACCV 2016)
Stars: ✭ 41 (-51.76%)
pyradoxState of the Art Neural Networks for Deep Learning
Stars: ✭ 61 (-28.24%)
DeepjazzDeep learning driven jazz generation using Keras & Theano!
Stars: ✭ 2,766 (+3154.12%)
SharkStockAutomate swing trading using deep reinforcement learning. The deep deterministic policy gradient-based neural network model trains to choose an action to sell, buy, or hold the stocks to maximize the gain in asset value. The paper also acknowledges the need for a system that predicts the trend in stock value to work along with the reinforcement …
Stars: ✭ 63 (-25.88%)
Keras GpKeras + Gaussian Processes: Learning scalable deep and recurrent kernels.
Stars: ✭ 218 (+156.47%)
seq2seq-autoencoderTheano implementation of Sequence-to-Sequence Autoencoder
Stars: ✭ 12 (-85.88%)
ChaseAutomatic trading bot (WIP)
Stars: ✭ 73 (-14.12%)
Sca Cnn.cvpr17Image Captions Generation with Spatial and Channel-wise Attention
Stars: ✭ 198 (+132.94%)
Opt MmdLearning kernels to maximize the power of MMD tests
Stars: ✭ 181 (+112.94%)
PixelcnnTheano reimplementation of pixelCNN architecture
Stars: ✭ 170 (+100%)