Running summarizing tools on a new article
Check the paper below, then start its synthesis.
Progress on photonic tensor processors based on time multiplexing and photoelectric multiplication
Ryan Hamerly (NTT (United States), Massachusetts Institute of Technology), Alexander Sludds (Massachusetts Institute of Technology), Liane Bernstein (Massachusetts Institute of Technology), Vivienne Sze (Massachusetts Institute of Technology), Joel Emer (Nvidia (United States), Massachusetts Institute of Technology), Marin Soljacic A (Massachusetts Institute of Technology), Dirk Robert Englund (Massachusetts Institute of Technology)
Abstract: Optical approaches to machine learning rely heavily on programmable linear photonic circuits. Since the performance and energy efficiency scale with size, a major challenge is overcoming scaling roadblocks to the photonic technology. Recently, we proposed an optical neural network architecture based on coherent detection. This architecture has several scaling advantages over competing approaches, including linear (rather than quadratic) chip-area scaling and constant circuit depth. We review the fundamental and technological limits to the energy consumption in this architecture, which shed light on the quantum limits to analog computing, which are distinct from the thermodynamic (e.g. Landauer) limits to digital computing. Lastly, we highlight a recent "digital" implementation of our architecture, which sheds light on the scaling challenges associated with controlling aberrations in the free-space optical propagation.