The matrix form of the RProp algorithm

Since the RProp algorithm uses if/else conditional statements while determining update values some special helper matrix-functions and helper matrices must be introduced. These functions will allow us to express the conditional statements more elegantly, only using matrix operations. Some matrices needed to make the above functions work: D: decision matrix, M: meta-gradient matrix, U: update […]

The Resilient Propagation (RProp) algorithm

The RProp algorithm is a supervised learning method for training multi layered neural networks, first published in 1994 by Martin Riedmiller. The idea behind it is that the sizes of the partial derivatives might have dangerous effects on the weight updates. It implements an internal adaptive algorithm which focuses only on the signs of the […]

Common extensions to Backpropagation

Preconditioning weights The outcome and speed of a learning process is influenced by the initial state of the network. However, it is impossible to tell which condition will be the most ideal. The commonly accepted way is initializing weights by uniformly distributed random numbers on the (0,1) interval. Preconditioning data Very often the training set […]

The Backpropagation algorithm

If there are multiple layers in a neural network the inner layers have neither target values nor errors. This problem remained unsolved until the 1970s when mathemathicians found the backpropagation algorithm to be usable for this particular problem. Backpropagation provides a way to train neural networks with any number of hidden layers. The neurons don’t […]

Feedforward neural networks

I am only covering feedforward neural networks in this project. General features of such networks are: Neurons are grouped into one input layer,  one or more hidden layers and an output layer. Neurons are not connecting to each other within the same layer. Each neuron of a hidden layer connects to all the neurons of […]