Abstract: The brain is nature’s most efficient computer, and the perfect blueprint for building better neural networks. This talk explores how principles of biological learning can revolutionize artificial intelligence: predictive coding that anticipates rather than reacts, spike-based computation that processes information through discrete events, and energy-aware learning that mirrors how the brain optimizes for minimal metabolic cost.
We apply these principles to neuromorphic neuromodulation, enhancing our ability to forecast and take preventative action against neural disease. But the implications extend beyond medicine: by translating these biological insights into computational frameworks, we enabled neuromorphic agents to make scientific discoveries in 2.5 hours that took the neuromorphic computing community half a decade to uncover.
Biography: Jason Eshraghian is an Assistant Professor and Fulbright Scholar in the Department of Electrical and Computer Engineering at the University of California, Santa Cruz. He is the developer of snnTorch, a Python library with over 500,000 downloads for training spiking neural networks. He is a dual-appointed IEEE CAS and EMBS Distinguished Lecturer, an Associate Editor of APL Machine Learning, the Chair of the IEEE Neural Systems and Applications Technical Committee, has been the recipient of seven IEEE Best Paper Awards, a Scientific Advisory Board Member of BrainChip and leads the Neuromorphic Agents Team at Conscium.
