Towards Bounding the Behavior of Neural Networks

Disciplines

Other Computer Engineering

Abstract (300 words maximum)

Recent advances in Artificial Intelligence (AI) have unlocked many new possibilities but have also brought with it many new challenges. While modern AI systems have been continuously exceeding expectations, our ability to interpret and understand their behavior lags behind. For example, an AI model trained to detect pneumonia from X-rays may fail in new hospitals because it learned to recognize hospital logos instead of medical patterns. Why do some succeed while others fail? Do they truly understand their tasks, or are they relying on patterns that may not always hold?

To enumerate the most informative explanations of a neuron’s behavior, we developed an improved approach to bounding the behavior of individual neurons within artificial neural networks. In this paper we demonstrate, both theoretically and empirically, the utility of our approach.

.

Academic department under which the project should be listed

CCSE - Computer Science

Primary Investigator (PI) Name

Arthur Choi

This document is currently not available here.

Share

COinS
 

Towards Bounding the Behavior of Neural Networks

Recent advances in Artificial Intelligence (AI) have unlocked many new possibilities but have also brought with it many new challenges. While modern AI systems have been continuously exceeding expectations, our ability to interpret and understand their behavior lags behind. For example, an AI model trained to detect pneumonia from X-rays may fail in new hospitals because it learned to recognize hospital logos instead of medical patterns. Why do some succeed while others fail? Do they truly understand their tasks, or are they relying on patterns that may not always hold?

To enumerate the most informative explanations of a neuron’s behavior, we developed an improved approach to bounding the behavior of individual neurons within artificial neural networks. In this paper we demonstrate, both theoretically and empirically, the utility of our approach.

.