As disruptive innovation continues to take place, it seems automation technology is becoming more certain over time, contrary to our now uncertain times – especially in Neuromorphic Computing.
The Australian Department of Defense has recently introduced the MANTIS (Mutual-Axis Neuromorphic Twin Imaging System) prototype, a new sensor that was developed by the Jericho Smart Sensing Lab (JSSL) at the University of Sydney in only three months.
Under a partnership between the Air Force and Defense Science and Technology Group, this prototype has shown the potential to measure speed and predict the trajectory and velocity of incredibly fast-moving objects.
This exploration has led to plans of future iterations where MANTIS could also be combined with a robotic eye to maneuver traditional camera frame limitation to large-portion surveillance capacity for airspace looking for air vehicles passively driving around.
What To Expect From The Next World-Beating Supercomputer?
With neuromorphic technologies, computers will be expected to solve problems faster while using less energy than our normal computers.
Sourced from Techradar, researchers at Sandia National Laboratories have demonstrated that neuromorphic computers that replicate the brain’s logic synthetically can solve more complex problems than those posed by AI.
“The natural randomness of the processes you list will make them inefficient when directly mapped onto vector processors like GPUs on next-generation computational efforts. Meanwhile, neuromorphic architectures are an intriguing and radically different alternative for particle simulation that may lead to a scalable and energy-efficient approach for solving problems of interest to us.” Said Brian Frankee, Sandia’s engineer and author of the new paper.
Sandia received over 50-million-chip Loihi research chips from Intel in the early 2020s to run their tests.
Although chips with artificial neurons are considered more cost-efficient and easy to utilize, it’s also undeniable that more data load needs to be transported off of neurochip processors. Eventually, the cost will increase along with the collected data, slowing the system until it finally stops working.
In the next supercomputer, we will be looking at new configurations of small neurons group with computed summary statistics, instead of raw data output.
Will the next supercomputer really mimic the human brain? Intel is looking to scale their neurons significantly, so bigger and better things are to come!
World’s First Neuromorphic Demonstration
The recognition goes to Western Sydney University and the United State Airforce Academy.
The world-first demonstration involved transmitting neuromorphic data from outer space.
Was it a success you may ask?
“Project Falcon Neuro is the first use of these sensors for earth observation from orbit, and the data received is the first neuromorphic data to be transmitted from space.”
“These cameras don’t take pictures, but rather sense changes and only send those when they happen. This method of sensing the visual world allows them to perform tasks that simply cannot be done with a conventional camera,” commented Associate Professor Gregory Cohen, ICNS’s lead researcher on the project.
This is definitely a Pioneer of Neuromorphic Technology.
What fascinating invention will we further unveil with Neuromorphic Technology? Will it be better than AI? Looks like the answer is a strong possible YES.
Stay close and don’t miss out on our next news and events to stay on top of the industry.
Ti2 is currently very focused on working with its global partners to secure stock and avoid long delay times in delivering products to their customers. Together with our trusted partners, we are here to provide solutions.
Please click here to email us your enquiry, we would like to hear from you.
Article inspired from gov.au, technology decisions, and techradar.