Samsung brings the world a step closer to develop neuromorphic chips that can better mimic the human brain. The result would be an effective return to “reverse-engineering the brain” as claimed by the company.
With the leading engineers and scholars from Samsung and Harvard University, the tech firm published a Perspective paper in Nature Electronics, titled ‘Neuromorphic electronics based on copying and pasting the brain,’ proposing a method that would “copy and paste” a brain’s neuron wiring map to 3D neuromorphic chips.
This method will use a breakthrough nanoelectrode array, developed by Donhee Ham, Fellow of Samsung Advanced Institute of Technology (SAIT) and Professor of Harvard University, Professor Hongkun Park of Harvard University to copy the brain’s neuron wiring map and paste it on a high-density three-dimensional network of solid-state memories or resistive RAM (RRAM).
Through this copy and paste approach, the ultimate aim is to create a memory chip that approximates the unique computing traits of the brain such as low power, facile learning, adaptation to the environment, and even autonomy and cognition – that have been beyond the reach of current technology. This could be a ‘shortcut’ to artificial intelligence systems that behave like real brains.
Taking a step further, the paper also suggests one possible way to speed up pasting the neuronal map by intracellularly recorded signals or directly downloading the map onto the memory chip.
Since the human brain has an estimated 100 billion or so neurons and more than a thousand-time synaptic connection, the chip will require 100 trillion or so memories which would be made possible by 3D integration of memories.
“The vision we present is highly ambitious,” said Dr. Ham. “But working toward such a heroic goal will push the boundaries of machine intelligence, neuroscience, and semiconductor technology.”
[…] you ever heard of Organic Neuromorphic Electronics? When we talk about the working of the human brain it works differently from a computer – while the human brain works with biological cells and […]