Learning from Imbalanced Data: Progress and Challenges
Speaker: Nitesh Chawla – Notre Dame, IN, United StatesTopic(s): Artificial Intelligence, Machine Learning, Computer Vision, Natural language processing
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. In this talk, I will share the progress on learning from imbalanced datasets, contrast with the “generative” synthetic data generation approaches, and reflect on open challenges and application domains. I will also discuss the similarities between fair ML and imbalanced data, and where they complement each other. I will conclude the talk with use-cases and applications.About this Lecture
Number of Slides: 45Duration: 60 minutes
Languages Available: English
Last Updated:
Request this Lecture
To request this particular lecture, please complete this online form.
Request a Tour
To request a tour with this speaker, please complete this online form.
All requests will be sent to ACM headquarters for review.