Past Events

PhD Defense Explanation-Driven Learning-Based Models for Visual Recognition Tasks
× Export Event Save iCal Send to Google Calendar Send to Yahoo Calendar Send to Outlook Live Send to Microsoft Outlook Save iCal Preserve formatting in description (only supported in some calendar applications) Close Friday, April 24, 2020, 11:00am - 12:30pm

Speaker: Zachary Daniels

Location : Remote via Webex

Committee: 

Prof. Dimitris Metaxas (Chair)

Prof. Konstantinos Michmizos

Prof. George Moustakides

Prof. Fuxin Li (External Member, Oregon State University)

Event Type: PhD Defense

Abstract: Safety-critical applications (e.g., autonomous vehicles, human-machine teaming, and automated medical diagnosis) often require the use of computational agents that are capable of understanding and reasoning about the high-level content of real-world scene images in order to make rational and grounded decisions that can be trusted by humans. Many of these agents rely on machine learning-based models which are increasingly being treated as black-boxes. One way to increase model interpretability is to make explainability a core principle of the model, e.g., by forcing deep neural networks to explicitly learn grounded and interpretable features. This talk will consist of three parts. First, I will provide a high-level overview of the field of explainable/interpretable machine learning and review some existing approaches for interpreting neural networks used for computer vision tasks. Second, I will introduce several novel approaches for making convolutional neural networks (CNNs) more interpretable by utilizing explainability as a guiding principle when designing the model architecture. Third, I will discuss some possible future research directions involving explanation-driven machine learning.

: 

Link:
https://rutgers.webex.com/rutgers/j.php?MTID=m2c8de56370e163e237d72908d3c475eb

ID:
798 066 597

Password:
uPaHcY6ju39