proposal for STAT946 (Deep Learning) final projects Fall 2015
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
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.
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.
Group members: Xinran Liu, Fatemeh Karimi, Deepak Rishi & Chris Choi
Title: Image Classification with Deep Learning
Description: Our aim is to participate in the Digital Recognizer Kaggle Challenge, where one has to correctly classify the Modified National Institute of Standards and Technology (MNIST) dataset of handwritten numerical digits. For our first approach we propose using a simple Feed-Forward Neural Network to form a baseline for comparison. We then plan on experimenting on different aspects of a Neural Network such as network architecture, activation functions and incorporate a wide variety of training methods.
Group members: Ri Wang, Maysum Panju
Title: Machine Translation Using Neural Networks
Description: The goal of this project is to translate languages using different types of neural networks and the algorithms described in "Sequence to sequence learning with neural networks." and "Neural machine translation by jointly learning to align and translate". Different vector representations for input sentences (word frequency, Word2Vec, etc) will be used and all combinations of algorithms will be ranked in terms of accuracy. Our data will mainly be from Europarl and Tatoeba. The common target language will be English to allow for easier judgement of translation quality.
Group members: Peter Blouw, Jan Gosmann
Title: Using Structured Representations in Memory Networks to Perform Question Answering
Description: Memory networks are machine learning systems that combine memory and inference to perform tasks that involve sophisticated reasoning (see here and here). Our goal in this project is to first implement a memory network that replicates prior performance on the bAbl question-answering tasks described in Weston et al. (2015). Then, we hope to improve upon this baseline performance by using more sophisticated representations of the sentences that encode questions being posed to the network. Current implementations often use a bag of words encoding, which throws out important syntactic information that is relevant to determining what a particular question is asking. As such, we will explore the use of things like POS tags, n-gram information, and parse trees to augment memory network performance.