By Christian J Meier
Can the human brain be simulated with a computer chip the size of a dinner plate? At least that’s what the Californian hardware manufacturer “Cerebras” makes us believe. Its golden-yellow chip “Wafer-Scale Engine-2” (WSE-2) should enable the largest deep learning networks to date, which roughly imitate the network of nerve cells and synapses in the human brain. WSE-2 enables a jump to deep learning networks “on the scale of the human brain,” according to Cerebras.