Introduction First of all, let me tell you this is part of the Coursera Machine Learning course. Here I will show how to implement a Neural Network Backpropation in Octave. I know there are already several options to do this in a very high level (TensorFlow), just focusing on inputs and outputs, but I would like to understand all the matrix and statistical fundamentals to later be able to choose the right strategies in high level programs. Backpropagation algorithm is a guided learning algorithm, i.e., we need to traning the Neural Network with real outputs in order to obtain good predictions.



Read more: Octave - Neural Network Back Propagation

Initialize variables

Initialize matrix with ones


Read more: Octave - Ploting equations



When we playing we see moving objects around the scenery, so today let's have a look how one of the most important pieces of that movement works: translation. There are many ways to perform the same maths, but the GPU must follow the defined pipeline and that's way we use matrices.



Read more: OpenGL tutorial. Performing translations and rotations

 02Sometimes matrix multiply operations are hard to see and understand. With this small application done in C++ in Qt I try to show how a matrix multiplication of range equal three is done. 

Read more: Visual Matrix Multiply