Assistant Professor, Computing & Mathematical Sciences, Caltech
11:00 AM
4011, Donald Bren Hall
Abstract: Self-Improving machine perception explores how we can build visual systems that do not just perceive the world, but continually improve at doing so. In…
Novel Applications of Item Response Theory in Environmental Health: Quantifying Cumulative Exposome Burden Scores for Harmonization and Report-Back
Shelley H Liu
Associate Professor, Population Health Science and Policy Icahn, School of Medicine at Mount Sinai
4:00 PM
6011, Donald Bren Hall
Abstract: Summary scores of cumulative chemical exposure burden are increasingly used in environmental health research. These summary scores can be useful for risk assessment, harmonization…
Learning Hyperparameters with Variational Bayes: The Case for a Data-Emphasized Objective
Michael Hughes
Associate Professor of Computer Science, Tufts University
11:00 AM
6011, Donald Bren Hall
Abstract: A basic problem in supervised machine learning is avoiding overfitting when training a big neural network classifier. To solve this today, practitioners often resort…
