Creating COM servers with CMake

I have recently come across a problem when I needed to use CMake to create a visual studio ATL COM Dll project using the MIDL compiler. I haven’t found an example anywhere I looked that provides a fully working solution, only bits and pieces here and there. So here I am posting a fully working […]

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 in 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 […]


Dear Reader, My aim with this blog is to publish some of the work I did on the field of Artificial Neural Networks. Between 2001 nd 2004 I developed a Neural Network trainer software that was able to distribute workload among multiple networked workstations. I think the idea deserves to be reserved for future reference. In the […]