Artificial synapse developed for brain-like computing with industry-compatible Nitride Semiconductors

Source: The post is based on the article “Artificial synapse developed for brain-like computing with industry-compatible Nitride Semiconductors” published in PIB on 29th January 2023

What is the News?

A team of scientists at Bengaluru’s Jawaharlal Nehru Centre for Advanced Scientific Research (JNCASR) have developed hardware for neuromorphic computing. 

They have used scandium nitride(ScN) to develop a device mimicking a synapse that controls the signal transmission as well as remembers the signal.

What is Neuromorphic computing?

​​Neuromorphic computing is a method of computer engineering in which elements of a computer are modeled after systems in the human brain and nervous system. 

Why Neuromorphic computing?

Traditional computers have physically separated memory storage and processing units. As a result, it takes enormous energy and time to transfer data between these units during an operation.

On the contrary, the human brain is a supreme biological computer that is smaller and more efficient due to the presence of a synapse (the connection between two neurons) that plays the role of both processor and memory storage unit.

The development of neuromorphic hardware aims at mimicking a biological synapse that monitors and remembers the signal generated by the stimuli.

How does Neuromorphic computing work?

The working of neuromorphic computing-enabled devices begins with the placement of Artificial Neural Networks (ANN) that comprise millions of artificial neurons. These neurons are similar to human brain neurons. 

These neurons pass signals to each other in layers, converting input into output through electric spikes or signals, based on the architecture of Spiking Neural Networks (SNN).

This allows the machine to mimic the neuro-biological networks in the human brain and perform tasks efficiently and effectively, such as visual recognition and data interpretation.

What are the advantages of Neuromorphic computing?

Rapid Response: Neuromorphic computers are specifically known for their rapid response system because their processing is highly rapid. Compared to traditional computers, neuromorphic computers are built to work like a human brain and so their rapid response system is a major highlight. 

Low Consumption of Power: Owing to the concept of Spiking Neural Networks (SNN), neuromorphic machines work when electric spikes or signals are passed through the artificial neurons. These artificial neurons work only when electric spikes are passed through them thus consuming low energy.