Dr. Ajay Chander
Vice President, Research
Fujitsu Labs of America
location_on United States
Member since 3 years
Share
Dr. Ajay Chander
Specialises In
Ajay Chander is an inventor and an educator who leads R&D teams in imagining and building new human-centric technologies and products. His work has spanned transparent AI, AI life assistants, digital healthcare and wellness, software security, and computational behavior design. Currently, Dr. Chander serves as the Vice President of Research at Fujitsu’s R&D lab in Silicon Valley and provides technical and thought/strategy leadership for all aspects of the interplay between technology and the human experience.
-
keyboard_arrow_down
Detecting Bias in AI: A Systems View & A Technique for Datasets
Dr. Ajay ChanderVice President, ResearchFujitsu Labs of America
Dr. Ramya SrinivasanMember of Research StaffFujitsu Labs of Americaschedule 3 years ago
45 Mins
Talk
Intermediate
Modern machine learning (ML) offers a new way of creating software to solve problems, focused on learning structures, learning algorithms, and data. In all steps of this process, from the specification of the problem, to the datasets chosen as relevant to the solution, to the choice of learning structures and algorithms, a variety of biases can creep in and compound each other. In this talk, we present a systems view of detecting Bias in AI/ML systems as analogous to the software testing problem. To start, a variety of expectations from an AI/ML system can be specified given its intended goals and deployment. Different kinds of bias can then be mapped to different failure modes, which can then be tested for during a variety of techniques. We will also describe a new technique based on Topological Data Analysis to detect bias in source datasets. This technique utilizes a persistence homology based visualization and is lightweight: the human-in-the-loop does not need to select metrics or tune parameters, and carry out this step before choosing a model. We’ll describe experiments on the German credit dataset using this technique to demonstrate its effectiveness.
-
-
No more submissions exist.
