New system can help machines think like humans
Inspired by brains, neural networks are composed of neurons, or nodes, and synapses, the connections between nodes.
Scientists have developed a new type of neural network chip that can dramatically improve the efficiency of teaching machines to think like humans. (Source: The Michigan Engineer News Center/ Wei Lu)
Scientists have developed a new type of neural network chip that can dramatically improve the efficiency of teaching machines to think like humans. The network, called a reservoir computing system, could predict words before they are said during conversation, and help predict future outcomes based on the present.
Reservoir computing systems, which improve on a typical neural network’s capacity and reduce the required training time, have been created in the past with larger optical components. Researchers from University of Michigan in the US created their system using memristors, which require less space and can be integrated more easily into existing silicon-based electronics.
No hay comentarios:
Publicar un comentario