Avatar

Gregory Cohen

Associate Professor of Neuromorphic Systems

Western Sydney University

Biography

I am an associate professor in Neuromorphic Systems at the International Centre for Neuromorphic Systems (ICNS) at Western Sydney University and program lead for neuromorphic algorithms and space applications.

My research interests include using biology-inspired cameras to image things in space, creating datasets to test neuromorphic systems, trying to figure out better ways to characterise their performance, and trying to build adaptive optics systems with neuromorphic systems.

Prior to returning to research from industry, I worked in several start-ups and established engineering and consulting firms including working as a consulting engineer in the field of large-scale HVAC from 2007 to 2009, as an electronic design engineer from 2009 to 2011, and as an expert consultant for Kaiser Economic Development Practice in 2012.

I am a pioneer of event-based and neuromorphic sensing for space imaging applications, unsupervised feature extraction, bio-inspired machine learning, and neuromorphic computation systems.

Interests

  • Event-based Vision Systems
  • Neuromorphic Engineering
  • Space Domain Awareness

Education

  • PhD in Neuromorphic Engineering, 2016

    WSU (Sydney, Australia) / UPMC (Paris, France)

  • BCom (Hons) Financial Analysis and Portfolio Management, 2010

    University of Cape Town, South Africa

  • MSc in Electrical Engineering, 2008

    University of Cape Town, South Africa

  • BSc in Electrical and Computer Engineering, 2006

    University of Cape Town, South Africa

Projects

Neuromorphic Space Imaging

Our pioneering work on the use of biology-inspired neuromorphic cameras for space imaging tasks, such space junk tracking, space domain awareness, and high-speed object tracking and detection

Robotic Foosball

Exploring real-world benchmarking problems for Neuromorphic Vision Systems through real-world games like foosball and pinball.

Adaptive Optics with Neuromorphic Sensors

Investigating the use of event-based vision sensors for high-speed, low-cost adaptive optics for space imaging applications.

The Astrosite

The Astrosite is a mobile containerized space domain awareness system powered by neuromorphic event-based camera technologies.

Datasets

A collection of datasets that we have generated for testing neuromorphic and deep learning problems.

Recent Posts

Two Satellites Just Avoided a Head on Smash. How Close Did They Come to Disaster?

An analysis article for The Conversation about the difficulties in predicting satellite collisions, and why this is such an important …

Videos

ICONS 2019 Talk - Active Sensing and its application to neuromorphic space imaging

Video of the keynote talk presented by Greg Cohen on the 24th July 2019 at the ICONS conference in Knoxville, Tennessee.

NICE 2019 Talk - Space imaging with event-based sensors

Video of the talk presented by Greg Cohen on the 28th March 2019 at the 2019 NICE Conference in Albany, NY.

Making space safer with neuromorphic cameras

An introduction to the benefits of using biology-inspired neuromorphic sensors for tracking space junk and satellites to make space a …

Benefits of Event-based Neuromorphic Sensing

Event-based cameras break the relationship between data rate and frame size and frame rate. This is demonstrated through a simulation …

Blabcoats Interview - Seeing the world through bio-inspired cameras (2018)

The team from Blabcoats interview me about biology-inspired cameras and how we are using these devices to solve real-world problems.

Contact