ronnypetson / abstractor_nn Goto Github PK
View Code? Open in Web Editor NEWEvolutionary search of artificial neural network architecture.
Evolutionary search of artificial neural network architecture.
This project is about finding topologies of artificial neural networks with evolutionary search and training the models of every found form with backpropagation. The topologies are constrained to be made of special layers called "abstractors", that are fully-connected layers with an arbitrary number of input unities (usually 2) and only one output unity - in the future it may be allowed to have as many output unities as necessary, but never more than the number of input unities. The fitness of a topolgy is a function of how well its models trained with backpropagation generalize to unseen data, their training cost, and their cost on testing data - the time used to reach a predetermined accuracy level may be included into the fitness too. A model in the path of the evolutionary search is a composition of abstractors and a final fully-connected layer between the last activations from the abstractor composition and the output unities.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.