A single layer analog optical neural network based on a 44 reconfigurable optical processor is analyzed through simulation. Using a stochastic optimization algorithm and a synthetic dataset, the network yields a final accuracy of 95.6%.

© 2019 The Author(s)

PDF Article


You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
Login to access OSA Member Subscription