arXiv · 1408.6949
Perceptrons with Hebbian learning based on wave ensembles in plastic potentials
Abstract
A general scheme to realize a perceptron for hardware neural networks is presented, where multiple interconnections are achieved by a superposition of Schrodinger waves. Spatially patterned potentials process information by coupling different points of reciprocal space. The necessary potential shape is obtained from the Hebbian learning rule, either through exact calculation or construction from a superposition of known optical inputs. This allows implementation in a wide range of compact optical systems, including: 1) any non-linear optical system; 2) optical systems patterned by optical lithography; and 3) exciton-polariton systems with phonon or nuclear spin interactions.
Explore related subjects
Keep this discovery
T. Espinosa-Ortega, T. C. H. Liew. 2015-02-25. Perceptrons with Hebbian learning based on wave ensembles in plastic potentials. https://doi.org/10.1103/physrevlett.114.118101
Cite the original work for its findings. Save a collection to share your selection of sources.