Machine Learning with a Multi Layer Perceptron

With all the hype about machine learning and artificial intelligence I thought it would be a good time to refresh my knowledge on the subject. Machine learning meets a lot of scepticism because it is mostly in the media for questionable tasks. Like all tools it can be used for evil things but it also has a lot of beneficial applications. I’m mostly interested in using it for computer graphics, games and tools.
I have implemented a multi layer perceptron in C++, using the Eigen template library for linear algebra. The code is quite simple, it allows to create a neural network with a variable number of layers and nodes per layer, to train the network, to query the network and to reverse query the network.

Continue reading “Machine Learning with a Multi Layer Perceptron”