YerevaNN/Dynamic-memory-networks-in-Theano
Implementation of Dynamic memory networks by Kumar et al. http://arxiv.org/abs/1506.07285
This project helps researchers and developers explore and experiment with Dynamic Memory Networks, a type of neural network designed for question answering tasks. It takes structured questions and related facts (like those in the bAbI tasks) as input and outputs the most probable answer. This is primarily useful for those working on natural language understanding and artificial intelligence research.
330 stars. No commits in the last 6 months.
Use this if you are a researcher or AI developer looking to implement, test, and extend Dynamic Memory Networks for question-answering scenarios.
Not ideal if you need a production-ready, off-the-shelf solution for general natural language processing or a pre-trained model for complex, real-world conversational AI.
Stars
330
Forks
108
Language
Python
License
MIT
Category
Last pushed
Dec 29, 2016
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/YerevaNN/Dynamic-memory-networks-in-Theano"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
localminimum/QANet
A Tensorflow implementation of QANet for machine reading comprehension
carpedm20/MemN2N-tensorflow
"End-To-End Memory Networks" in Tensorflow
HKUST-KnowComp/R-Net
Tensorflow Implementation of R-Net
domluna/memn2n
End-To-End Memory Network using Tensorflow
allenai/bi-att-flow
Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that...