Warning: You are using the test version of PyPI. This is a pre-production deployment of Warehouse. Changes made here affect the production instance of TestPyPI (testpypi.python.org).
Help us improve Python packaging - Donate today!

Allows to create and train fully connected feedforward deep neural networks in a simple way.

Project Description

Neural Network Builder The neural network class is in NeuralNet.py. It allows to easily create fully connected feedforward networks of any size allowed by available memory. It uses numpy arrays as the primary data structure for the weight matrices. With this class you can create deep neural networks very quickly (see some of the example files to see how to use it).

Release History

Release History

History Node

0.2a4

History Node

0.2a3

History Node

0.2a2

History Node

0.2a1

History Node

0.2a0

This version
History Node

0.1.3

History Node

0.1.3a0

Supported By

WebFaction WebFaction Technical Writing Elastic Elastic Search Pingdom Pingdom Monitoring Dyn Dyn DNS Sentry Sentry Error Logging CloudAMQP CloudAMQP RabbitMQ Heroku Heroku PaaS Kabu Creative Kabu Creative UX & Design Fastly Fastly CDN DigiCert DigiCert EV Certificate Rackspace Rackspace Cloud Servers DreamHost DreamHost Log Hosting