Samsung Electronics scientists and Harvard University scholars have come up with a new concept of mimicking the brain neural network onto chips.
Their research paper titled, ‘Neuromorphic electronics based on copying and pasting the brain’, has been published by Nature Electronics.
“The essence of this vision is to ‘copy’ the functional synaptic connectivity map of a mammalian neuronal network using advanced neuroscience tools and then ‘paste’ this map onto a high-density three-dimensional network of solid-state memories” says the paper.
The researchers claim that this could lead memory chips to duplicate the brain’s autonomy and cognition better.
The scholars claim that their concept takes off on the original research of neurotrophic computing that aimed to replicate the neural structure of the brain.
The paper suggests a way to copy the brain’s neuronal connection map using a unique nanoelectrode array developed by Dr.Donhee Ham and Professor Hongkun Park, both from Harvard, to paste this map onto a high-density three-dimensional network of solid-state memories, the technology for which Samsung has been a world leader.
The scientists want to reverse engineer the neuron map of the brain.
The neurons and their wiring map is responsible for the brain’s functions. Thus a knowledge of the map is the key to reverse-engineering the brain.
“The idea is to paste the copied neuronal map to a network of non-volatile memories – such as commercial flash memories that are used in our everyday life in solid-state drives (SSD), or ‘new’ memories such as resistive random access memories (RRAM) – by programming each memory and its carry through based on the strength of each neuronal connection in the copied map,” says a press statement by Samsung.
However, idea to reality is a long way off as the human brain is made up of billions of neutrons and thousands of synaptic connections. Computing that onto memory chips means handling at least trillions 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.”
Leveraging its leading experience in chip manufacturing, Samsung is planning to continue its research into neuromorphic engineering in order to extend Samsung’s leadership in the field of next-generation AI semiconductors.
Dr. Donhee Ham, Fellow of Samsung Advanced Institute of Technology (SAIT) and Professor of Harvard University, Professor Hongkun Park of Harvard University, Sungwoo Hwang, President and CEO of Samsung SDS and former Head of SAIT, and Kinam Kim, Vice Chairman and CEO of Samsung Electronics are the co-corresponding authors of the paper.
No Comments