PhD, Electrical & Computer Engineering
Rochester Institute of TechnologyResearch: trustworthy neuromorphic computing; testing and reliability of spiking neural networks.
Curriculum vitae
PhD Student, Electrical & Computer Engineering
Rochester Institute of Technology
PhD researcher developing testing and evaluation methods for dependable AI systems, with primary emphasis on spiking neural networks, neuromorphic computing, fault tolerance, and safety-relevant system behavior.
Research: trustworthy neuromorphic computing; testing and reliability of spiking neural networks.
Artificial intelligence, deep learning, healthcare analytics, and human–computer interaction.
Developing testing and evaluation frameworks for spiking neural networks to improve the reliability, fault tolerance, and performance of neuromorphic systems.
Researched social-agent mediated interaction in the NSF AI-ALOE Institute; developed ML models from learner interaction data and investigated cognitive approaches to human–agent understanding.
DOI: 10.1145/3787109.3815284
Efficient approaches for evaluating the dependability of neuromorphic systems under hardware faults.
Improving the reliability of spiking neural networks that learn continually in imperfect and changing environments.
Evaluating practical approaches for dependable oversight and intervention in increasingly capable AI systems.
BlueDot-funded project examining evaluation design and safety-benchmark limitations across bio, cyber, and chemical risk domains.
Led product development and delivered full-stack software and ML-enabled analytics systems.
Designed and delivered institutional information systems serving more than 5,000 users.