Inverse design of convolutional neural networks via nanophotonic kernels

Abstract

We proposed an ultra-compact neural network based on inversely designed photonic kernels, which has the advantages of a small footprint, high computing speed, and low power consumption. The core layers of the neural network, composed of automatically optimized photonic multiplication kernels and addition kernels, can perform arbitrary photonic computations at the speed of the light wave, offering more advantages than their electronic counterparts. Furthermore, the convolution, pooling, and fully-connected layers can be realized by the appropriate permutation of the proposed optical kernels. We constructed an all-optical convolutional neural network with a high accuracy of 97.7% for recognizing handwritten digits. Our results could significantly promote the inverse design of photonic neural networks.

KEYWORDS:

• Inverse design
• adjoint method
• photonic convolution neural network
• photonic computation
• handwritten digits recognition

Acknowledgement

The authors acknowledge support from the open project from the state key laboratory of the high-power semiconductor laser.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by the National Natural Science Foundation of China (NSFC) [grant number 61975182].