GitHub - stoerr/simple-neural-network-learning: This contains an explorational implementation of learning in neural networks, as well as some simple helper classes (automatic differentation, statistics, timing). It covers the RProp algoritm and an experiment to extend the gradient descent idea with using the second derivation to automatically select a good step width.

stoerr / simple-neural-network-learning Public

This contains an explorational implementation of learning in neural networks, as well as some simple helper classes (automatic differentation, statistics, timing). It covers the RProp algoritm and an experiment to extend the gradient descent idea with using the second derivation to automatically select a good step width.