IEEE Swiss CAS/ED Sponsored Lecture by Dr. Kwabena Boahen
Speaker: Dr. Kwabena Boahen
Affiliation: Stanford University
Title: Scaling Knowledge Processing from 2D Chips to 3D Brains
Abstract: Artificial intelligence (AI) now advances by performing twice as many multiplications every two months, but the semiconductor industry tiles twice as many multipliers on a chip every two years. Moreover, the returns from tiling these multipliers ever more densely now diminish because signals must travel relatively farther and farther. Thus, communicating now consumes much more energy and generates much more heat than computing does. Although travel can be shortened by stacking multipliers tiled in two dimensions in the third dimension, such a solution acutely reduces the available surface area for dissipating heat. My recent reconception of the brain’s fundamental unit of computation cuts communication by moving away from synaptocentric learning to dendrocentric learning. Synaptocentric learning weights input signals precisely across an entire arbor of dendrite to discriminate spatial patterns of input. Current AI, by using dot-products to emulate synaptic weighting, realizes this 60-year-old conception but produces dense output signals. Dendrocentric learning orders input signals meticulously along a short stretch of dendrite to detect a particular spatiotemporal pattern of inputs. I will illustrate how dendrocentric learning AI, by using a string of ferroelectric transistors to emulate a stretch of dendrite, could signal sparsely and thus enable knowledge processing to scale from 2D chips to 3D brains.
Biography: Kwabena Boahen is a Professor of Bioengineering, Electrical Engineering, and by courtesy Computer Science at Stanford University; an investigator in Stanford’s Bio-X Institute, System X Alliance, and Wu Tsai Neurosciences Institute; and the founding director of Stanford’s Brains in Silicon Lab. His group models the nervous system computationally to elucidate principles of neural design at the cellular, circuit, and systems levels; and synthesizes neuromorphic electronic systems that scale energy-use with size as efficiently as the brain does. He earned a doctorate in Computation and Neural Systems at the California Institute of Technology in 1997. From 1997 to 2005 he was on the faculty of University of Pennsylvania, Philadelphia PA. His research has resulted in over a hundred publications, including a cover story in Scientific American featuring his lab’s work on a silicon retina and a silicon tectum that “wire together” automatically (May 2005). He has received several distinguished honors, including a Packard Fellowship for Science and Engineering (1999) and a National Institutes of Health Director’s Pioneer Award (2006). He was elected a fellow of the American Institute for Medical and Biological Engineering (2016) and of the Institute of Electrical and Electronic Engineers (2016) in recognition of his lab’s work on Neurogrid, an iPad-size platform that emulates the cerebral cortex in biophysical detail and at functional scale, a combination that hitherto required a supercomputer. He has trained over twenty graduate students and mentored four postdoctoral researchers, including the designers of IBM’s TrueNorth chip and NeuraLink’s implantable chip and the founders of Femtosense and Dexterity, two Silicon Valley start-ups.
Date and Time
Location
Hosts
Registration
- Date: 09 Sep 2024
- Time: 02:00 PM to 03:00 PM
- All times are (UTC+02:00) Bern
-
Add Event to Calendar
- University of Zurich
- Winterthurerstrasse 190
- Zurich, Switzerland
- Switzerland 8057
- Building: 35
- Room Number: F51
- Contact Event Host
- Co-sponsored by Institute of Neuroinformatics, UZH and ETHZ
Agenda
13:50 Welcome
14:00 - 15:15 Lecture and Q&A