The official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We develop a method for analyzing emerging functional modularity in neural networks based on differentiable weight masks and use it to point out important issues in current-day neural networks.

Stars: ✭ 25 (+66.67%)

Mutual labels: rnn

sequence-rnn-py

Sequence analyzing using Recurrent Neural Networks (RNN) based on Keras

Stars: ✭ 28 (+86.67%)

Mutual labels: rnn

Music-generation-cRNN-GAN

cRNN-GAN to generate music by training on instrumental music (midi)

Stars: ✭ 38 (+153.33%)

Mutual labels: rnn

Customer-Feedback-Analysis

Multi Class Text (Feedback) Classification using CNN, GRU Network and pre trained Word2Vec embedding, word embeddings on TensorFlow.

Stars: ✭ 18 (+20%)

Mutual labels: rnn

chainer-notebooks

Jupyter notebooks for Chainer hands-on

Stars: ✭ 23 (+53.33%)

Mutual labels: rnn

solar-forecasting-RNN

Multi-time-horizon solar forecasting using recurrent neural network

Stars: ✭ 29 (+93.33%)

Mutual labels: rnn

ECGClassifier

CNN, RNN, and Bayesian NN classification for ECG time-series (using TensorFlow in Swift and Python)

Stars: ✭ 53 (+253.33%)

Mutual labels: rnn

VariationalNeuralAnnealing

A variational implementation of classical and quantum annealing using recurrent neural networks for the purpose of solving optimization problems.

Stars: ✭ 21 (+40%)

Mutual labels: rnn

SpeakerDiarization RNN CNN LSTM

Speaker Diarization is the problem of separating speakers in an audio. There could be any number of speakers and final result should state when speaker starts and ends. In this project, we analyze given audio file with 2 channels and 2 speakers (on separate channels).

Stars: ✭ 56 (+273.33%)

Mutual labels: rnn

Tensorflow-RNN-Tutorial

Tensorflow RNN Tutorial

Stars: ✭ 24 (+60%)

Mutual labels: rnn

theano-recurrence

Recurrent Neural Networks (RNN, GRU, LSTM) and their Bidirectional versions (BiRNN, BiGRU, BiLSTM) for word & character level language modelling in Theano

Stars: ✭ 40 (+166.67%)

Mutual labels: rnn

DeepLearning-Lab

Code lab for deep learning. Including rnn,seq2seq,word2vec,cross entropy,bidirectional rnn,convolution operation,pooling operation,InceptionV3,transfer learning.

Stars: ✭ 83 (+453.33%)

Mutual labels: rnn

View All Similar Projects ➔

Question Answering NLP with character-level RNN

The different models will first be challenged with the bAbI dataset from FAIR and the SQuAD dataset from Stanford.

Content:

Name	Description
/babi	babi dataset and utilities
/squad	squad dataset and utilities
/qrn	contains the QRN cell
char2word.py	Char2Word-only module (on bAbI dataset)
qrn.py	implementation of the QRN model (on bAbI dataset)
char2word_qrn.py	implementation of the QRN model w/ Char2Word module (on bAbI dataset)
mango_squad.py	implementation of the QRN model w/ Char2Word module (on SQuAD dataset)

Usage (with the bAbI dataset):

Query-Reduction Network with Char2Word:

python char2word_qrn.py

Query-Reduction Network without Char2Word:

python qrn.py

Usage (with the SQuAD dataset):

Query-Reduction Network with Char2Word:

python mango_squad.py

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

yfletberliac / mango

Programming Languages

Labels

Projects that are alternatives of or similar to mango

Question Answering NLP with character-level RNN

Content:

Usage (with the bAbI dataset):

Usage (with the SQuAD dataset):