Neuromorphic memory device consisting of bottom volatile and top nonvolatile memory layers emulating neuronal and synaptic properties, respectively.
CREDIT: KAIST
Simultaneous emulation of neuronal and synaptic properties promotes the development of brain-like artificial intelligence
Researchers have reported a nano-sized neuromorphic memory device that emulates neurons and synapses simultaneously in a unit cell, another step toward completing the goal of neuromorphic computing designed to rigorously mimic the human brain with semiconductor devices.
Neuromorphic computing aims to realize artificial intelligence (AI) by mimicking the mechanisms of neurons and synapses that make up the human brain. Inspired by the cognitive functions of the human brain that current computers cannot provide, neuromorphic devices have been widely investigated. However, current Complementary Metal-Oxide Semiconductor (CMOS)-based neuromorphic circuits simply connect artificial neurons and synapses without synergistic interactions, and the concomitant implementation of neurons and synapses still remains a challenge. To address these issues, a research team led by Professor Keon Jae Lee from the Department of Materials Science and Engineering implemented the biological working mechanisms of humans by introducing the neuron-synapse interactions in a single memory cell, rather than the conventional approach of electrically connecting artificial neuronal and synaptic devices.
Similar to commercial graphics cards, the artificial synaptic devices previously studied often used to accelerate parallel computations, which shows clear differences from the operational mechanisms of the human brain. The research team implemented the synergistic interactions between neurons and synapses in the neuromorphic memory device, emulating the mechanisms of the biological neural network. In addition, the developed neuromorphic device can replace complex CMOS neuron circuits with a single device, providing high scalability and cost efficiency.
The human brain consists of a complex network of 100 billion neurons and 100 trillion synapses. The functions and structures of neurons and synapses can flexibly change according to the external stimuli, adapting to the surrounding environment. The research team developed a neuromorphic device in which short-term and long-term memories coexist using volatile and non-volatile memory devices that mimic the characteristics of neurons and synapses, respectively. A threshold switch device is used as volatile memory and phase-change memory is used as a non-volatile device. Two thin-film devices are integrated without intermediate electrodes, implementing the functional adaptability of neurons and synapses in the neuromorphic memory.
Professor Keon Jae Lee explained, “Neurons and synapses interact with each other to establish cognitive functions such as memory and learning, so simulating both is an essential element for brain-inspired artificial intelligence. The developed neuromorphic memory device also mimics the retraining effect that allows quick learning of the forgotten information by implementing a positive feedback effect between neurons and synapses.”
Original Article: Neuromorphic memory device simulates neurons and synapses
More from: Korea Advanced Institute of Science and Technology
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Brain-like artificial intelligence
- Artificial intelligence could help brick-and-mortar stores achieve a new golden age
entrepreneurs and investors — the arrival of artificial intelligence in retail shopping. AI is promising to transform the way Americans shop. According to a study by RetailWire and Brain Corp, almost ...
- Neural networks don’t work like the human brain because they ‘learn’ differently
We’re told neural networks ‘learn’ the way humans do. A neuroscientist explains why that’s not the case — and why AI can't think like us yet.
- How artificial intelligence (AI) improves healthcare access and equality
Investors are paying particular attention to companies like Vara and Paradromics, who are already striving to improve access, cost, and ultimately healthcare outcomes. According to Lu Zhang, head of ...
- Evaluating brain MRI scans with the help of artificial intelligence
Diseases like Alzheimer’s or other neurodegenerative ... This is where technical innovations such as artificial intelligence can offer support in interpreting clinical images. One such tool is the ...
- Artificial Intelligence: A gift for healthcare
From diagnosis to treatment, from prevention to therapeutics, artificial intelligence has made many things possible which had been unachievable before.
Go deeper with Google Headlines on:
Brain-like artificial intelligence
Go deeper with Bing News on:
Neuromorphic computing
- Spinoff Prize looks for Irish companies to enter €30,000 competition
The Spinoff Prize will focus on companies founded on life science or physical science research, which can include digital tech such as AI, deep learning, neuromorphic computing and quantum computing.
- TEMPO AI chip tapes out with videantis processor platform
GmbH, a leading supplier of deep learning, computer vision, image processing, and video coding solutions, today announced the tape-out of a low-power AI chip based on its v-MP6000UDX unified ...
- Build-a-satellite program could fast track national security space missions
Satellites equipped with remote sensing technology execute many critical national security missions, from detecting explosions to tracking sea ice, but until now it could take a team years to move ...
- Multilevel polarization switching in ferroelectric thin films
for instance towards neuromorphic computing. Modern electronics is a digital world, where information is generated, stored, and processed in the form of zeros and ones. Thus, to fulfill their ...
- A Photonic Quantum Device Took Microseconds to Do a Task a Conventional Computer Would Spend 9,000 Years On
The trick was to introduce loops of optical fibers to delay photons so they can interfere at specific spots important for quantum computation.