Skip to main content

Abstract: Andre van Schaik

Neuromorphic Engineering Needs Closed-Loop Benchmarks

Neuromorphic engineering aims to build (autonomous) systems by mimicking biological systems. It is motivated by the observation that biological organisms—from algae to primates—excel in sensing their environment, reacting promptly to their perils and opportunities. Furthermore, they do so more resiliently than our most advanced machines, at a fraction of the power consumption. It follows that the performance of neuromorphic systems should be evaluated in terms of real-time operation, power consumption, and resiliency to real-world perturbations and noise using task-relevant evaluation metrics. Yet, following in the footsteps of conventional machine learning, most neuromorphic benchmarks rely on recorded datasets that foster sensing accuracy as the primary measure for performance. Sensing accuracy is but an arbitrary proxy for the actual system's goal—taking a good decision in a timely manner. Moreover, static datasets hinder our ability to study and compare closed-loop sensing and control strategies that are central to survival for biological organisms. This talk makes the case for a renewed focus on closed-loop benchmarks involving real-world tasks. Such benchmarks will be crucial in developing and progressing neuromorphic Intelligence. The shift towards dynamic real-world benchmarking tasks should usher in richer, more resilient, and robust artificially intelligent systems in the future.

Short Bio

André van Schaik received the M.Sc. degree in electrical engineering from the University of Twente, Enschede, The Netherlands, in 1990 and the Ph.D. degree in electrical engineering from the Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland, in 1998.
He has authored more than 200 publications, invented more than 35 patents, and is a founder of three start-up companies: VAST Audio, Personal Audio, and Heard Systems.
Image of Andre
In 1998 he was a postdoctoral research fellow in the Department of Physiology at the University of Sydney, funded by fellowship from the Garnett Passe and Rodney Williams memorial foundation. In 1999 he became a Senior Lecturer in the School of Electrical and Information Engineering at the University of Sydney and promoted to Reader in 2004.
In 2011 he became a research professor at Western Sydney University and leader of the Biomedical Engineering and Neuromorphic Systems (BENS) Research Program in the MARCS Institute for Brain, Behaviour, and development. In 2018, he became the Director of the International Centre of Neuromorphic Engineering. His research focuses on neuromorphic engineering and computational neuroscience.

Back to the Schedule