proposal for STAT946 (Deep Learning) final projects Fall 2015

From statwiki
Revision as of 20:58, 12 October 2015 by Trttse (talk | contribs)
Jump to navigation Jump to search

Project 0: (This is just an example)

Group members:first name family name, first name family name, first name family name

Title: Sentiment Analysis on Movie Reviews

Description: The idea and data for this project is taken from http://www.kaggle.com/c/sentiment-analysis-on-movie-reviews. Sentiment analysis is the problem of determining whether a given string contains positive or negative sentiment. For example, “A series of escapades demonstrating the adage that what is good for the goose is also good for the gander , some of which occasionally amuses but none of which amounts to much of a story” contains negative sentiment, but it is not immediately clear which parts of the sentence make it so. This competition seeks to implement machine learning algorithms that can determine the sentiment of a movie review

Project 1:

Group members: Sean Aubin, Brent Komer

Title: Convolution Neural Networks in SLAM

Description: We will try to replicate the results reported in Convolutional Neural Networks-based Place Recognition using Caffe and Google-net. As a "stretch" goal, we will try to convert the CNN to a spiking neural network (a technique created by Eric Hunsberger) for greater biological plausibility and easier integration with other cognitive systems using Nengo. This work will help Brent with starting his PHD investigating cognitive localisation systems and object manipulation.

Project 2:

Group members: Tim Tse

Title: Sleep Stage Classification with Noisy Labels

Description: This project is a an idea that my supervisor recommended me to try. Here, we wish to design some sort of learning algorithm (presumably a neural network) to classify one of five sleep stages that one is in from their EEG signal. We have also been playing around with the idea that we can use an unsupervised learning algorithm to learn features and hence, eliminate the need for hand-tailored features. At the same time, we are thinking that we can possibly leverage crowdsourcing to create training cases. The data with inevitably be quite noisy so we also wish to factor noise management into the design.