Discover a new breed of AI neuromorphic computing

7th October 2019
Posted By : Alex Lynn
Discover a new breed of AI neuromorphic computing

BrainChip Holdings has announced that Peter Van der Made, CTO and founder of BrainChip, will speak to audiences at two upcoming industry events. Van der Made will discuss its flagship technology, Akida, an advanced Spiking Neural Network (SNN) processor.

Akida’s AI processing capabilities are used for functions like training, learning, and inferencing and deliver faster results, while consuming only a tiny fraction of the power resources of traditional AI processing. These sessions are intended for anyone interested in discovering more about artificial general intelligence and the most advanced SNN processor on the market today.

Van der Made has been at the forefront of computer innovation for 40 years. His upcoming appearances includes the Perth Machine Learning Group Meetup October 17th at 5:45pm (AWST), Tank Stream Labs, Ernst and Young Building Level 5 in Perth.

Titled ‘Akida: Event-Based Neural Networks for Fast Inference at the Edge with Low Power Consumption,’ Van der Made will address attendees of each event about Akida’s use of SNNs, which offer more rapid training, higher accuracy, and lower compute overhead than traditional neural nets. This is an important feature in the world outside of the Internet, where large datasets are not available. 

“There are a number of exciting things I’m looking forward to sharing with attendees of these events about SNNs in general and the opportunities to be gained by real-time learning that are offered by implementing Akida,” said Van der Made. “Applications for Akida are wide ranging – from object detection, face recognition, fault detection and keyword spotting, for instance. Akida learns from experience, autonomously, just like a human, to get us to AGI in a way that deep learning never will.”

With the proliferation of intelligence into edge devices, there is a new and growing need for fast, small, and power-efficient neural network processors. By performing neural processing and memory accesses on the edge, Akida vastly reduces the computing resources required of the host CPU. 

This unprecedented efficiency not only delivers faster results, it consumes only a tiny fraction of the power resources of traditional AI processing, reducing the high environmental and economic costs of running hyperscale data centres. Akida is available as an SNN processing chip as well as a licensable technology that can be integrated with other hardware and devices for applications such as surveillance, advanced driver assistance systems (ADAS), autonomous vehicles (AV), vision guided robotics, drones, augmented and virtual reality (AR/VR), acoustic analysis, and Industrial Internet-of-Things (IoT).


You must be logged in to comment

Write a comment

No comments




Sign up to view our publications

Sign up

Sign up to view our downloads

Sign up

Vietnam International Defense & Security Exhibition 2020
4th March 2020
Vietnam National Convention Center, Hanoi
The Sensor Show 2020
16th June 2020
Germany Messe Munich