Date: October 28, 2016
Speaker: Prof. Sameer Singh (UC Irvine)
Location: DBH 6011
Time: 11am – 12pm
Host: Harry Xu
Title: Towards Intuitive Explanations and Interactions with Black-box Machine Learning
Abstract: Machine learning is at the forefront of many recent advances in science and technology, enabled in part by the sophisticated models and algorithms that have been recently introduced. However, as a consequence of this complexity, machine learning essentially acts as a black-box as far as users are concerned. It is incredibly difficult to understand, predict, or “fix” the behavior of machine learning models that have been deployed. In this talk, I propose interpretable representations that allow users and machine learning models to interact with each other: enabling machine learning models to provided explanations as to why a specific prediction was made and enabling users to inject domain knowledge into machine learning. The first part of the talk introduces an approach to estimate local, interpretable explanations for black-box classifiers and describes an approach to summarize the behavior of the classifier by selecting which explanations to show to the user. The second part of the talk focuses on relation extraction, an important subtask of natural language processing where the goal is to identify the types of relations between entities that are expressed in text. Here we focus on using first-order logic statements as the interpretable representation between the user and machine learning. We introduce approaches to both explain the relation extractor using logical statements and to inject symbolic domain knowledge, if provided by the user as first-order logic statements, into relational embeddings to improve the predictions. I present experiments to demonstrate that an interactive interface is effective in providing users an understanding of, and an ability to improve, complex black-box machine learning systems.
Bio: Sameer Singh is an Assistant Professor of Computer Science at the University of California, Irvine. He is working on large-scale and interactive machine learning applied to information extraction and natural language processing. Till recently, Sameer was a Postdoctoral Research Associate at the University of Washington. He received his PhD from the University of Massachusetts, Amherst in 2014, during which he also interned at Microsoft Research, Google Research, and Yahoo! Labs on massive-scale machine learning. He was selected as a DARPA Riser, won the grand prize in the Yelp dataset challenge, has been awarded the Yahoo! Key Scientific Challenges and the UMass Graduate School fellowships, and was a finalist for the Facebook PhD fellowship. Sameer has published more than 30 peer-reviewed papers at top-tier machine learning and natural language processing conferences and workshops.
Return to the Fall 2016 CS Seminar Series Schedule