Skip to content

MXNet Implementation of DeepMind's Neural Arithmetic Logic Units (NALU)

License

Notifications You must be signed in to change notification settings

gautam1858/Neural-Arithmetic-Logic-Units

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 

Repository files navigation

Neural Arithmetic Logic Units

nalu

MXNet implementation of Neural Arithmetic Logic Units by Andrew Trask, Felix Hill, Scott Reed, Jack Rae, Chris Dyer and Phil Blunsom using MNIST dataset

Training

from mxnet import *

# Training and saving the model
python nalu.py action train

Prediction

from mxnet import *

# Performing prediction using the saved mxnet model
python nalu.py action predict

Note : Default action is train: python nalu.py

TODO: Reinforcement Learning Experiments

About

MXNet Implementation of DeepMind's Neural Arithmetic Logic Units (NALU)

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages