New Delhi: A team of researchers from the IIT- Delhi and IIT-Bombay has built a new neuromorphic hardware using magnetic materials.
Neuromorphic hardware uses specialized computing architectures that reflect the structure (morphology) of neural networks from the bottom up: dedicated processing units emulate the behavior of neurons directly in hardware, and a web of physical interconnections (bus-systems) facilitate the rapid exchange of information.
This concept is inspired by the human brain, where biological neurons and synapses work together in a similar way. Specialized neuromorphic devices are less flexible than universal central processing units (CPUs), but offer exceptional performance and energy efficiency during the training and inference for deep neural networks.
It involves delivering the speech data to the cloud over the internet, processing the data in the cloud, and then providing the response to the device. But due to slow internet speed, power outages, and other factors, speech data is frequently lost. This may change with the advent of neuromorphic computing, where local hardware with built-in memory executes all operations, hence preventing data loss while simultaneously reducing power consumption.
"We have high hopes that the study contributes significantly to both the India Semiconductor mission as well as Make-in-India mission of the government of India," said Prof Pranaba Kishor Muduli, Department of Physics, IIT Delhi, in a statement.
(To receive our E-paper on WhatsApp daily, please click here. To receive it on Telegram, please click here. We permit sharing of the paper's PDF on WhatsApp and other social media platforms.)