Semester of Graduation

Summer 2026

Degree

Master of Science in Computer Science (MSCS)

Department

Computer Science and Engineering

Document Type

Thesis

Abstract

SNNs are a foundational model in neuromorphic computing, where efficient architectures must be discovered for a wide range of applications. Evolutionary methods, such as EONS, offer a flexible approach to this search but become increasingly difficult to scale as task complexity grows due to the rapidly expanding combined topology–parameter search space and associated memory demands. To address this challenge, we propose a co-evolutionary ensemble framework in which a population of candidate SNNs is evolved with fitness defined by each network’s marginal contribution to group performance. Grounded in cooperative game theory and difference evaluation functions from multiagent systems, this formulation provides a principled credit assignment mechanism that rewards networks that consistently improve ensemble performance and penalizes redundancy, encouraging complementary specialization during evolution rather than relying on post-evolved combination of independently trained networks. We evaluate the approach on classification, regression, and control tasks under μCaspian neuromorphic hardware constraints, where co-evolved ensembles achieve statistically significant improvements over both single-network evolution and post-evolved ensembles across all tasks, with the most pronounced gains observed in control, where standard evolution fails to discover effective policies and co-evolution enables a qualitative transition to near-optimal performance.

Date

7-6-2026

Committee Chair

Ghawaly, James

LSU Acknowledgement

1

LSU Accessibility Acknowledgment

1

Download

Share

COinS