Bar-Ilan physicists engineer AI to increase confidence in autonomous vehicles

• Published date: 16 April 2024
• Author: JUDY SIEGEL-ITZKOVICH
• Publication title: Jerusalem Post, The: Web Edition Articles (Israel)

Now, a new measure for distinguishing between high- and low- confidence artificial intelligence (AI) decision-making by researchers at Bar-Ilan University (BIU) in Ramat Gan has been shown to significantly boost the safety and reliability of autonomous vehicles and other applications

Described by its authors as a "milestone in AI," it addresses a fundamental question: Can deep-learning architectures achieve greatly above-average confidence for a significant portion of inputs while maintaining overall average confidence?

The study's findings provide an emphatic "yes!" to this question, marking a significant leap forward in AI's ability to discern and respond to varying levels of confidence in classification tasks. By leveraging insights into the confidence levels of deep architectures, the research team has opened new avenues for real-world applications, ranging from autonomous vehicles to healthcare.

The scope of AI and how it can benefit the world of technology

The study has just been published under the title "Advanced confidence methods in deep learning" in the journal Physics A by a team headed by Prof. Ido Kanter from BIU's physics department and the Gonda (Goldschmied) Multidisciplinary Brain Research Center.

Ella Koresh, an undergraduate student and a contributor to the research, explained the practical...