Brain imaging data (fMRI) pattern recognition

The main goal of this project is to explore the capacity of Artificial Neural Networks for classification of cognitive patterns, in particular, prediction when the subject is reading a sentence versus perceiving a picture during single window of trial. In addition, we identify which features to include for classifier input and a number of issues about efficient computation with the large data set. Multilayer feed-forward perceptron network classifier is used for classification of cognitive activities. The code is implemented in MATLAB programming language using Netlab Toolbox, a Matlab library for artificial neural networks.