CogniGron Seminar: Gert Cauwenberghs (UCSD, USA) - "Towards Efficient Neuromorphic Learning and Inference at Scale"

The human brain offers an existence proof of general intelligence realized by hierarchical assemblies of massively parallel, yet imprecise and slow compute elements that operate near fundamental limits of noise and energy efficiency. We continue to be guided by biology in pursuing their instantiations in neuromorphic very large-scale integrated electronic circuits. These neuromorphic realizations have evolved from highly specialized, task-specific compute-in-memory neural and synaptic crossbar array architectures that operate near the efficiency of synaptic transmission in the human brain, to large tiles of such neurosynaptic cores assembled into hierarchically interconnected networks for general-purpose learning and inference. By combining extreme efficiency of local interconnects (grey matter) with great flexibility and sparsity in global interconnects (white matter), these assemblies are capable of realizing a wide class of deeply layered and recurrent neural architectures with embedded local plasticity for on-line learning, at a fraction of the computational and energy cost of GPGPU implementations. A proof-of-concept reconfigurable memristive neurosynaptic core integrated in 130nm CMOS-RRAM demonstrates a record 74 TMACS/W efficiency in visual pattern classification and reconstruction.

About Gert Cauwenberghs
Dr. Gert Cauwenberghs pioneered the design and implementation of highly energy efficient, massively parallel microchips that emulate function and structure of adaptive neural circuits in silicon. Recently the Cauwenberghs group demonstrated synaptic arrays in silicon for adaptive template-based visual pattern recognition operating at less than a femtojoule of energy per synaptic operation, exceeding the nominal energy efficiency of synaptic transmission in the human brain. A main focus of current work is on extending integrated sensing and actuation to dynamical interfaces to neural and brain activity. Recent developments include implantable and wireless microelectrode arrays for distributed recording of electrical and chemical neural activity, and biopotential sensor arrays and integrated signal processing for electroencephalogram and electrocorticogram functional brain imaging. These dynamical interfaces between living and artificial nervous systems offer tremendous opportunities for transformative, integrative neuroscience and neuroengineering that are the focus of continued research in the Cauwenberghs laboratory, in collaboration with partners in academia, industry, and the clinical sector.

Gert Cauwenberghs received the M.Eng. degree in applied physics from University of Brussels, Belgium, in 1988, and the M.S. and Ph.D. degrees in electrical engineering from California Institute of Technology, Pasadena, in 1989 and 1994. He is Professor of Bioengineering at University of California San Diego, where he co-directs the Institute for Neural Computation. Previously, he held positions as Professor of Electrical and Computer Engineering at Johns Hopkins University, Baltimore Maryland, and as Visiting Professor of Brain and Cognitive Science at Massachusetts Institute of Technology, Cambridge.

He is a Francqui Fellow of the Belgian American Educational Foundation, and received the National Science Foundation Career Award in 1997, Office of Naval Research Young Investigator Award in 1999, and Presidential Early Career Award for Scientists and Engineers (PECASE) in 2000. He was Distinguished Lecturer of the IEEE Circuits and Systems Society in 2003-2004, and chaired its Analog Signal Processing Technical Committee in 2001-2002. He currently serves as Associate Editor for IEEE Transactions on Biomedical Circuits and Systems, and IEEE Transactions on Neural Systems and Rehabilitation Engineering. He is Senior Editor for the IEEE Sensors Journal.

For more information go to his webpage