Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a DMD based approaches to realize energetically efficient light coupling into a multi-core fiber realizing a unique design for in-fiber optical neural networks. Neurons and synapses are realized as individual cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in Erbium-doped cores mimics synaptic interactions. In order to dynamically and efficiently couple light into the multi-core fiber a DMD based micro mirror device is used to perform proper beam shaping operation. The beam shaping reshapes the light into a large set of points in space matching the positions of the required cores in the entrance plane to the multi-core fiber.
|Original language||American English|
|Title of host publication||Emerging Digital Micromirror Device Based Systems and Applications IX|
|Editors||Michael R. Douglass, Benjamin L. Lee|
|State||Published - 2017|
|Event||Emerging Digital Micromirror Device Based Systems and Applications IX - San Francisco, United States|
Duration: 30 Jan 2017 → 31 Jan 2017
|Name||Proceedings of SPIE - The International Society for Optical Engineering|
|Conference||Emerging Digital Micromirror Device Based Systems and Applications IX|
|Period||30/01/17 → 31/01/17|
Bibliographical notePublisher Copyright:
© 2017 SPIE.
- Neural networks
- beam shaping
- multi-core fiber
- optical computing