Abstract

With artificial intelligence (AI) becoming ubiquitous in a broad range of application domains, the opacity of deep learning models remains an obstacle to adaptation within safety-critical systems. Explainable AI (XAI) aims to build trust in AI systems by revealing important inner mechanisms of what has been treated as a black box by human users. This thesis specifically aims to improve the transparency and trustworthiness of deep learning algorithms by combining attribution methods with image segmentation methods. This thesis has the potential to improve the trust and acceptance of AI systems, leading to more responsible and ethical AI applications. An exploratory algorithm called ESAX is introduced and shows how performance greater than other top attribution methods on PIC testing can be achieved in some cases. These results lay a foundation for future work in segmentation attribution.

Thesis Completion

2023

Semester

Spring

Thesis Chair/Advisor

Ewetz, Rickard

Degree

Bachelor of Science in Electrical Engineering (B.S.E.E.)

College

College of Engineering and Computer Science

Department

Electrical and Computer Engineering

Degree Program

Electrical Engineering

Language

English

Access Status

Open Access

Release Date

11-15-2023

Share

COinS