Speaker

Nitesh Chawla

Abstract

Despite over two decades of progress, imbalanced data is still considered a significant challenge for contemporary machine learning models. With modern advances and rapid developments in deep learning, countering the problem of imbalanced data has become extremely important. The two main approaches to address this issue are based on loss function modifications and instance resampling, typically based on Generative Adversarial Networks (GANs) that may suffer from mode collapse. Therefore, there is a need for an oversampling method that is specifically tailored to deep learning models, can work on raw images while preserving their properties, and is capable of generating high quality, artificial images that can enhance minority classes and balance the training set. In this presentation, I'll discuss our recent work DeepSMOTE - a novel oversampling algorithm for deep learning models. It is simple, yet effective in its design, and demonstrates significant performance improvement over its peers.

Bio

Nitesh Chawla is the Frank M. Freimann Professor of Computer Science and Engineering at Notre Dame, and Founding Director of the Lucy Family Institute for Data and Society. His research is focused on machine learning, data science, and network science, and is motivated by the question of how technology can advance the common good through interdisciplinary research. He is the recipient of the  IEEE CIS Outstanding Early Career Award; the IBM Watson Faculty Award, the IBM Big Data, and Analytics Faculty Award, National Academy of Engineering New Faculty Fellowship, and 1st Source Bank Technology Commercialization Award.  In recognition of the societal and community impact of his research, he received the Rodney F Ganey Award and Michiana 40 under 40 honor.  He is co-founder of Aunalytics, a data science software and cloud computing company.

[Click on image below ↓  for talk recording]