FINAL PROJECT TOPICS

You can pick one of the following topics, modify one topic, or propose an entirely different topic. Send email with your proposal to yann and jhuangfu ( [ a t ] cs.nyu.edu) with you topic proposal.

• Oversampling photos: take of bunch of high-resolution/hihg-quality photos. Subsample them (e.g. make them half the original size) and compress them (aggressively) with JPEG. Train a neural net (e.g. a convolutional net) to reconstruct 2x2 patches of the high-qual/high-res image from the corresponding pixel and its surroundings (e.g. 11x11 pixels) in the compressed/low-res image.
• Photo Orientation: collect lots of image from the web, from your personnal photo collection, or from CDROM collections. Make a training set (1) by cropping a maximally-sized square area from the center of each picture, (2) normalizing each square image to a small size (e.g. 40x40 pixels), (3) rotating each image by 90, 180, and 270 degrees. Train a machine (e.g. a convolutional net) to predict the roation angle. After training, you can use the machine to automatically rotate photos so they are right-side up.
• Pruned Mean-Square SVM: build an SVM-like architecture: one layer of gaussian units (with one unit per training sample), followed by a linear classifier (or one per class for multiclass classification). Train the weights with means squared error (and/or logistic regression). Prune the weights using the "Optimal Brain Damage" technique (see http://books.nips.cc/papers/files/nips02/0598.djvu ). Retrain, Re-prune... Test this method on the MNIST dataset of handwritten digits ( http://yann.lecun.com/exdb/mnist/ ).
• Siamese Nets: train two identical copies of a neural net (with identical weights) to produce similar output vectors when they are presented with images of a single person, and to produce different outputs when they are presented with images of two different persons. Use one the human face databases available on the Web (e.g. the AT&T/ORL dataset http://www.uk.research.att.com/facedatabase.html). The network can subsequently be used for face recognition.
• Belief Propagation for Factor Graph: Write a general factor graph class in Lush, and implement the belief propagation algorithm (sum product algorithm for factor graphs in log space).
• first come, first served. More project topics to come....

Other project ideas that have been proposed (and taken): training an edge detector from manually annotated images, training a machine to predict keystrokes,....