The most popular and comprehensive Open Source ECM platform
Chip designers are are creating chips that mimic the neurons and synapses in the human brain. The goal is to make chips that are smarter and more energy efficient than today’s standard generation of chips. The chips process data asynchronously and use an event-driven processing model.
Chris Eliasmith, a professor at the University of Waterloo, was quoted in the Communication of the ACM to say that “neuromorphic chips introduce a level of parallelism that doesn’t exist in today’s hardware, including GPUs and most AI accelerators… Neuromorphic designs allow scaling that hasn’t been possible in the past. We’re able to go far beyond what today’s systems can do.”
Adam Stieg, associate director of the California NanoSystems Institute at UCLA, said that “the ability to perform computation and learning on the device itself, combined with ultra-low energy consumption, could dramatically change the landscape of modern computing technology.”
Neuromorphic chips could make an impact in areas like image and speech recognition, IoT and edge devices, robotics and autonomous vehicles. But the technology is still in the research phase with no commercial products — it’s expected to take at least another couple of years before commercial chips will be available.
Stieg said that “neuromorphic computing aims to open up an entirely new and unexplored area of computing. It could allow us to do things with computers that we couldn’t have imagined in the past.”
Sunny Bains, lecturer at University College London, said that “if some niche applications for neuromorphic computing prove successful, such as keyword spotting or sensory processing, then that could create a virtuous circle of investment, development, innovation and optimization. The end result could be a viable industry with its own version of Moore’s Law, one that is more tightly connected with the needs of cognitive and intelligence tasks.”