A new computer architecture, under development, is well prepared to handle increased data loads from artificial intelligence. The designs draw on theories from the human brain and considerably outperform conventional computers in comparative studies
Today's computers are built on the von Neumann architecture, which feature a central processor that executes logic and arithmetic, a memory unit, storage, and input and output devices. The IBM team drew on three different levels of inspiration from the brain, namely the connection between brain's memory and processing, the brain’s synaptic network structures and the dynamic and stochastic nature of neurons and synapses.
The new ‘Phase change memory’ is a nano-scale memory device built from compounds of Ge, Te and Sb, sandwiched between electrodes. These compounds display diverse electrical properties dependent on their atomic arrangement. According to researchers, they could achieve 200 times faster performance in the phase change memory computing systems, in contrast to conventional computing systems.