Presented by
Thiago Serra
Department of Analytics and Operations Management
School of Management – Bucknell University
Thursday, September 16
Abstract: Neural networks have been successfully applied to complex predictive modeling tasks in areas such as computer vision and natural language processing. On the one hand, they have been shown to be a very powerful mathematical modeling tool. On the other hand, we may still need an unreasonably large neural network in order to obtain a predictive model with good accuracy in many cases. How can we reconcile those two facts?
Pizza served at 11:40 in terrace Holmes 327.