webeng

DrQA

Reading Wikipedia to Answer Open-Domain Questions

SeqMatchSeq

dynamic-coattention-network

Tensorflow implementation of Dynamic Coattention Networks for Question Answering.

Qazy

Lazy Loading - No SEO Negative Impact

end-to-end-negotiator

Deal or No Deal? End-to-End Learning for Negotiation Dialogues

vqa.pytorch

Visual Question Answering in Pytorch

relational-networks

Pytorch implementation of "A simple neural network module for relational reasoning" (Relational Networks)

SNNs

Tutorials and implementations for "Self-normalizing networks"

dnc

A TensorFlow implementation of the Differentiable Neural Computer.

dqa-net

Diagram question answering system described in "A Diagram is Worth a Dozen Images"

sonnet

TensorFlow-based neural network library

bnlstm

Batch normalized LSTM for tensorflow

evolution-strategies-starter

Code for the paper "Evolution Strategies as a Scalable Alternative to Reinforcement Learning"

deep_qa

A deep NLP library, based on Keras / tf, focused on question answering (but useful for other NLP too)

article-date-extractor

Extracts an online article's publication date

faiss

A library for efficient similarity search and clustering of dense vectors.

youtube-8m

Starter code for working with the YouTube-8M dataset.

lectures

Oxford Deep NLP 2017 course

Neural-Dialogue-Generation

neural-style

Torch implementation of neural style algorithm

scnn

Segment-CNN: A Framework for Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs

awesome-deep-vision

A curated list of deep learning resources for computer vision

recurrent-batch-normalization

Attentive_reader

Simple Attentive Reader Code

public_plstm

Phased LSTM

openai-gemm

Open single and half precision gemm implementations

rasa

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

bi-att-flow

Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to achieve a query-aware context representation without early summarization.

ladder

Ladder network is a deep learning algorithm that combines supervised and unsupervised learning

learning-to-learn

Learning to Learn in TensorFlow