Publication Date

Spring 2026

Degree Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Engineering

Advisor

Bernardo Flores; Kaikai Liu; Magdalini Eirinaki

Abstract

Neural networks are a recent popular technology inspired from human brains. Much of their popularity arises from how they excel in reasoning and logic, and are generally rather efficient in their tasks. With those strengths, they are frequently used in transportation and business among many other fields. However, neural networks have many factors that can deteriorate their performance, one of the most critical being weight corruption. Therefore, it is of utmost importance to detect and handle them as soon as possible so as to minimize the negative impact on a network’s performance. The optimization of neural networks would be especially valuable in some key applications, namely in medical fields, or other fields that involve human life. It would also be valuable in the pursuit of artificial general intelligence, where neural networks must achieve peak efficiency to rival human intellect. To that end, this work explores adding a system of weight controllers in the network. Weight controllers would observe the weights, quickly detecting them, then handling them, if there are any weights that are corrupted. In the experiments of this work, the model performance recovery, as well as the system overhead of weight controllers was observed when used with a variety of different models in different use cases.

Download

Share

COinS