I have always used MATLAB for neural networks design. Can you suggest any other useful software? Which books or papers provide a good reference for different types of neural training algorithms or internal architectures?
PyBrain is a modular Machine Learning Library for Python. Its goal is to offer flexible, easy-to-use yet still powerful algorithms for Machine Learning Tasks and a variety of predefined environments to test and compare your algorithms.
PyBrain is short for Python-Based Reinforcement Learning, Artificial Intelligence and Neural Network Library. In fact, we came up with the name first and later reverse-engineered this quite descriptive "Backronym". http://pybrain.org/
others links and libs http://neuralnetworksanddeeplearning.com/chap1.html
If you want to use python then I suggest you use it along with Theano and Numpy. Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. If you want faster computation Theano also supports the use of GPUs.
The following links may help;
http://deeplearning.net/.
There is an excellent document featuring most popular deep learning algorithms and their implementation using Theano. The document is attached herewith.
In Poland we use user-friendly Statistica. In this program You can make both an automatical and manual neural network. But I work only in polish version. You can contact with producer: http://www.statsoft.com/ I don't know what is a prace, becouse we have educational version.