abeoliver / reverselearning Goto Github PK
View Code? Open in Web Editor NEWThe Input Optimization Algorithm
License: MIT License
reverselearning's People
Contributors
Stargazers
Watchers
Forkers
jadanercolireverselearning's Issues
Need way to split weights and biases into independent values
As of now, weights, biases, and inputs are matrices of values all optimized at once. It would be nice to be able to make certain values constant
Wiki needs to be updated with new results / features
The wiki section of GitHub seems really cool to me so whenever we make something new, discover something, etc., write a wiki page about it.
Learn Rates are the key / problem
On some addition network testing I noticed something very odd.
If I trained with a learning rate of about .001 or above, the weights shot toward infinity leaving 'nan'.
However, if I used .0001 it worked perfectly.
Weirdest part, in the Jupyter Version, this didn't happen. Using .001 worked perfectly and there were no problems. WHAT IS THE DIFFERENCE BETWEEN THE TWO CASES?
Image backprop optimization leaves REALLY weird result
This is supposed to be a 9
Find code in branch InputBackprop file /NeuralNetworks/Notebooks/MNIST Input Backprop.ipynb
Network not training weights
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 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. 📊📈🎉
-
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 ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.