.png){kind=icon}
.png){kind=icon}
Return
Optical micro-phase-shift dropvolume in a diffractive deep neural network
.png){kind=icon}
PRE
AI
DOI：10.1364/OL.486384.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
To provide a desirable number of parallel subnetworks as required to reach a robust inference in an active modulation diffractive deep neural network, a random micro-phase-shift dropvolume that involves five-layer statistically independent dropconnect arrays is monolithically embedded into the unitary backpropagation, which does not require any mathematical derivations with respect to the multilayer arbitrary phase-only modulation masks, even maintaining the nonlinear nested characteristic of neural networks, and generating an opportunity to realize a structured-phase encoding within the dropvolume. Further, a drop-block strategy is introduced into the structured-phase patterns designed to flexibly configure a credible macro-micro phase dropvolume allowing for convergence. Concretely, macro-phase dropconnects concerning fringe griddles that encapsulate sparse micro-phase are implemented. We numerically validate that macro-micro phase encoding is a good plan to the types of encoding within a dropvolume.& COPY; 2023 Optica Publishing Group
Keywords:
BACKPROPAGATION
Journal
IF:
3.3
Papers:
4.0W
Citations:
7.6W