Neural Networks for Face Recognition

Machine Learning course 15-681, Homework 5

Professor Tom Mitchell, CMU, Fall 1995

This assignment gives you the opportunity to experiment with neural network learning for face recognition. From this page you can access over 600 face images, a C implementation of the neural network Backpropagation algorithm, documentation, and the homework assignment itself.

The assignment document describes the assignment in detail.

The code directory contains the source code for the neural network Backpropagation algorithm described in Chapter 5 of the textbook Machine Learning (thanks to Jeff Shufelt for the initial implementation of this code.)

The face images directory contains the face image data in PGM format, or download a compressed tar file of all the images (only ~10.5MB!), or a compressed tar file of only the one-quarter size images (~0.5MB - most students used only these images in order to save computation time). See the assignment document above for a description of the images.

The trainset directory contains the specifications of training and test sets referred to in the assignment document.

Visitors from outside CMU are invited to use this material free of charge for any educational purpose, provided attribution is given in any lectures or publications that make use of this material.