NETRIUS Deep Chaos
Abstract
Artificial intelligence, and deep learning in particular, is increasingly becoming a critical component in our national infrastructure. It is imperative that techniques used to train these models be consistent in their predictions. Fooling these systems with small perturbations to the input data is a well-known problem. Identifying and characterizing regions of sensitivity is less understood in the Al domain, but well studied in nonlinear dynamics mathematics. We seek to investigate whether deep neural networks are chaotic, and, if so, can they be stabilized?
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 20, 2021
- Accession Number
- AD1153246
Entities
People
- Mohammed Eslami