Research news on Neuromorphic AI hardware

Neuromorphic AI hardware encompasses brain-inspired computing systems that implement neural network primitives directly in physical substrates to achieve extreme energy efficiency and low latency. Architectures use devices such as memristors, magnetic tunnel junctions, electrochemical memories, photonic and microwave components, and organic or superconducting neurons to realize synapses, neurons, and compute-in-memory operations. These platforms support spiking and analog neural computation, on-chip learning, and specialized sensory and cognitive functions, targeting applications from edge intelligence and autonomous systems to large-scale AI acceleration and brain–computer interfaces.

Hardware

Expanding computing resources with light for AI datacenters

A team of Korean researchers has developed the world's first technology that can freely connect and disconnect core computing resources such as memory and accelerators with "light" in next-generation artificial intelligence ...

Hardware

Ultra-compact photonic AI chip operates at the speed of light

Australian researchers have built an ultra-compact artificial intelligence (AI) chip that is able to make calculations using the power of light, at the speed of light. The nano photonic chip prototype, which harnesses the ...

page 1 from 19