University of Michigan, July 30, 2018
Memristors enable memory and processing in the same device. However, memristors can have resistances that are on a continuum. Researchers at the University of Michigan got around the problem by digitizing the current outputs and mapped large mathematical problems into smaller blocks within the array, called “memory-processing units,” improving the efficiency and flexibility of the system. This is particularly useful for implementing machine learning and artificial intelligence algorithms, weather prediction and other matrix-based operations… read more.
Memristor based equation solver could cut energy used by 100 times for longer lasting smartphones
Posted in Memristor and tagged Computation.