In Partial Fulfillment of the Requirements for the Degree of Master of Science
will defend his thesis
Comparing Association Rules and Deep Neural Networks on Medical Data
Deep neural networks are today's most popular tool for building predictive models. A decade ago, the most popular technique for this was association rule mining. In this work we carefully compare these two techniques in an effort to have a more effective way to predict heart disease, a multi-prediction problem. Both techniques require significant knowledge, manual tuning, and experimentation to determine optimal parameters. Our goal was to build a predictive model that is at least as good as association rules. Promising results were obtained for some examples, while others still remain unclear. Making predictive models with medical data continues to be a challenging problem to solve.
Date: Monday, November 11, 2019
Time: 3:00 - 4:00 PM
Place: PGH 218D
Advisor: Dr. Carlos Ordonez
Faculty, students, and the general public are invited.