The Deep Learning program is a semester-long program to be presented in the fall of 2019. The program will focus on statistical strategies for improving machine learning. There is vast interest in automated methods for complex data analysis. However, there is a lack of consideration of: (1) interpretability; (2) uncertainty quantification; (3) applications with limited training data; and (4) selection bias. Statistical methods can achieve (1)-(4) through a change in focus.
Program Working Groups
-
- Working Group I: Bayesian Methods in Deep Learning and Architecture Search, (Leader: David Dunson)
- Working Group II: Interpretable Deep Networks, (Leader: Cynthia Rudin)
- Working Group III: Deep Learning for Dimension Reduction, (Leader: Xiuyuan Cheng)
- Working Group IV: Novel Applications, (Leader: Martin Mohlenkamp)
- Working Group V: Teaching Deep Learning, (Leader: David Banks)
- Working Group VI: Statistical Optimality, (Leader: Guang Cheng)
- Working Group VII: Uncertainty Quantification for Deep Models, (Leader: Anindya Bhadra)
- Working Group VIII: Regularization Techniques for Training Deep Networks , (Leader: Sorin Mitran)
Questions: email [email protected]