We demonstrate that optical time-dynamics are equivalent to a recurrent neural network and that they can be trained for high-performance on complex classification tasks, paving the way for passive analog machine learning processors.

© 2020 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