Ph.D. Candidate in Computer Science
Saint Louis University
Pioneering cross-modal neuromorphic computing with 719× energy efficiency breakthrough. Advancing brain-inspired AI systems for edge computing and autonomous applications.
I am a Ph.D. candidate in Computer Science at Saint Louis University, specializing in neuromorphic computing and cross-modal artificial intelligence. As leader of Project Phasor, I conduct groundbreaking research on memory mechanisms in spiking neural networks across different sensory modalities.
My research has achieved extraordinary recognition, including a 2025 Congressional invitation to advise on neuromorphic computing policy, membership in the NIH BRAIN Initiative, and international media coverage of my cross-modal neuromorphic work, which achieves up to 719× energy efficiency over traditional neural networks (per peer-reviewed results).
My work spans peer-reviewed conference papers, a journal submission under review, and poster presentations at premier venues (NICE, ICONS, NeurIPS workshops), bridging neuroscience, artificial intelligence, and public policy to advance energy-efficient AI systems for real-world deployment.
Cross-Modal Neuromorphic Computing
Leading multi-institutional research investigating memory mechanisms in spiking neural networks across visual and auditory modalities. First comprehensive cross-modal ablation study demonstrating modality-specific specialization and design principles for neuromorphic hardware.
Brain-Inspired Computing
Contributing to the nation's largest neuroscience research program, applying neuromorphic computing principles to advance understanding of brain function and develop transformative neurotechnologies for AI systems.
Congressional Testimony
Invited expert witness to United States Congress (2025) on neuromorphic computing policy. Advised on national AI strategy, technological competitiveness, and applications for national security and edge computing systems.
Accepted, IEEE Computer (DOI: 10.1109/MC.2026.3696092) | arXiv:2512.18575, December 2025
First comprehensive cross-modal ablation study of memory mechanisms in SNNs. Peak 719.0× energy efficiency with 99.3% spike sparsity; best cross-modal accuracy 89.99% (97.72% visual, 82.25% auditory). Featured in Quantum Zeitgeist.
IEEE NICE 2026 Conference
IEEE BMI 2026
XAI4Science Workshop @ AAAI 2026 (Regular Track, 6–8 pages)
DeepMath 2025 (Conference on the Mathematical Theory of Deep Neural Networks)
ACM ICONS 2026 Student Poster Competition
Women in Machine Learning Workshop @ NeurIPS 2025
MATH-AI 2025 Poster
Master's Thesis, African University of Science and Technology, 2021
Invited to United States Congress to advise on neuromorphic computing policy and national AI strategy
Research featured in Quantum Zeitgeist covering cross-modal neuromorphic energy efficiency gains
Selected for premier federal neuroscience research program advancing brain-inspired technologies
Leading governance and partnerships for Open Neuromorphic (ONM), a 2,700+ member global community
Leading multi-institutional neuromorphic computing research with NCSU, Luxmuse AI, and independent researchers
Competitive research funding for graduate studies at African University of Science and Technology
Email: blessing.effiong@slu.edu
Office: School of Science and Engineering
Saint Louis University
St. Louis, Missouri, USA