Machine-learning system based on light could yield more powerful, efficient large language models

An MIT machine-learning system demonstrates greater than 100-fold improvement in energy efficiency and a 25-fold improvement in compute density compared with current systems.

Related Keywords

Canada ,Dirk Englund ,Alexander Sludds ,Ian Christen ,Tobias Heuser ,Lamia Ateshian ,Ryan Hamerly ,Liane Bernstein ,Stephan Reitzensttein ,Niels Heermeier ,Jamesa Lott ,Ronald Davis ,Zaijun Chen ,Logan Wright ,Natural Sciences ,University Of Southern California ,Us National Science Foundation ,Engineering Graduate Fellowship Program ,Volkswagen Foundation ,Us National Defense Science ,Research Inc ,Research Laboratory Of Electronics ,Quantum Photonics Laboratory ,Engineering Research Council Of Canada ,Yale University ,Department Of Electrical Engineering ,Materials Research Laboratory ,Us Army Research Office ,Nature Photonics ,Research Laboratory ,Electrical Engineering ,Computer Science ,Photonics Laboratory ,Materials Research ,Technische Universitat ,Research Office ,Defense Science ,Science Foundation ,Engineering Research Council ,Chatgpt ,Enerative Ai ,Hotonics ,Optical Neural Networks ,Eep Neural Networks Dnns ,Ertical Surface Emitting Lasers ,Ptoelectronic Processors ,