nalu's People
Forkers
lesaffreanalu's Issues
No Hidden->Hidden NAC Works Better
I ran experiments where NAC/NALU was used as a hidden-to-hidden layer (as you have implemented) as well as experiments where the hidden -> hidden was purely additive (each NAC simply added/subtracted into the next hidden state). Both work, but the latter works much better.
Default code doesn't train correctly
Hey, thanks for creating this repo. A small issue I'd like to point out, though. I was using this repo to run NAC.py, and running NAC.py as is the network doesn't train at all (never goes below 1800 loss) very often, depending on the random initialization.
Did you do any parameter changes locally in order to make it more stable?
Thanks
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.