Compatible Learning for Deep Photonic Neural Network

by   Yong-Liang Xiao, et al.

Realization of deep learning with coherent optical field has attracted remarkably attentions presently, which benefits on the fact that optical matrix manipulation can be executed at speed of light with inherent parallel computation as well as low latency. Photonic neural network has a significant potential for prediction-oriented tasks. Yet, real-value Backpropagation behaves somewhat intractably for coherent photonic intelligent training. We develop a compatible learning protocol in complex space, of which nonlinear activation could be selected efficiently depending on the unveiled compatible condition. Compatibility indicates that matrix representation in complex space covers its real counterpart, which could enable a single channel mingled training in real and complex space as a unified model. The phase logical XOR gate with Mach-Zehnder interferometers and diffractive neural network with optical modulation mechanism, implementing intelligent weight learned from compatible learning, are presented to prove the availability. Compatible learning opens an envisaged window for deep photonic neural network.



page 5

page 7

page 9


Unitary Learning for Deep Diffractive Neural Network

Realization of deep learning with coherent diffraction has achieved rema...

Optical Phase Dropout in Diffractive Deep Neural Network

Unitary learning is a backpropagation that serves to unitary weights upd...

Backpropagation through nonlinear units for all-optical training of neural networks

Backpropagation through nonlinear neurons is an outstanding challenge to...

Training Neural Networks to Produce Compatible Features

This paper makes a first step towards compatible and hence reusable netw...

Cascadable all-optical NAND gates using diffractive networks

Owing to its potential advantages such as scalability, low latency and p...

An optical diffractive deep neural network with multiple frequency-channels

Diffractive deep neural network (DNNet) is a novel machine learning fram...

Fiber Nonlinearity Mitigation via the Parzen Window Classifier for Dispersion Managed and Unmanaged Links

Machine learning techniques have recently received significant attention...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.