Tag Archives: memristors

Memristors power quick-learning neural network

ANN ARBOR — A new type of neural network made with memristors 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. (more…)

Read More

New Silicon Memory Chip Developed

The first purely silicon oxide-based ‘Resistive RAM’ memory chip that can operate in ambient conditions– opening up the possibility of new super-fast memory – has been developed by researchers at UCL.

Resistive RAM (or ‘ReRAM’) memory chips are based on materials, most often oxides of metals, whose electrical resistance changes when a voltage is applied – and they “remember” this change even when the power is turned off.

ReRAM chips promise significantly greater memory storage than current technology, such as the Flash memory used on USB sticks, and require much less energy and space. (more…)

Read More