Deep learning with light
A new computing architecture enables advanced machine-learning computations to be performed on a low-power, memory-constrained edge device. The technique may enable self-driving cars to make decisions in real-time while only using a fraction of the energy that is currently demanded by their power-hungry on-board computers.
Dirk Englund Ieuan Allen Saumil Bandyopadhyay Alexander Sludds Research Laboratory Of Electronics Lincoln Laboratory
Source: mit.edu