Assigning semantic meaning to machine derived competency controlling topics

Olga Babko-Malaya; Michael Planer; Letitia Li

doi:10.1117/12.2663821

12 June 2023 Assigning semantic meaning to machine derived competency controlling topics

Olga Babko-Malaya, Michael Planer, Letitia Li

Proceedings Volume 12538, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications V; 125380L (2023) https://doi.org/10.1117/12.2663821
Event: SPIE Defense + Commercial Sensing, 2023, Orlando, Florida, United States

Abstract

In the DARPA Competency Aware Machine Learning program, the MindfuL™ system derived machine level ‘conditions’ (topics in a multi-modal Hierarchical Dirichlet Process model) that are aligned with and predictive of the competency of a CNN obstacle detection component of a self-driving car. These competency controlling conditions don’t map directly into human level concepts, which limits the utility of this explainable AI approach. This paper discusses methods to increase understanding and trust of the competency assessment and the ML agent itself by automatically generating labels for these conditions that will be meaningful and useful to the human operator.

Conference Presentation

Citation Download Citation

Olga Babko-Malaya, Michael Planer, and Letitia Li "Assigning semantic meaning to machine derived competency controlling topics", Proc. SPIE 12538, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications V, 125380L (12 June 2023); https://doi.org/10.1117/12.2663821

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available