Competitive photonic neural networks

Brunner, Daniel

doi:10.1038/s41566-021-00803-0

Cited by 17 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A detailed review of this topic is beyond the scope of this paper. We refer the reader to excellent and detailed reviews [189][190][191] that already exist. In any case, we believe that highlighting the main steps in this field, with the latest research results, can be useful in order to understand all the aspects of the fruitful interplay between photonics and AI.…”

Section: Photonic Computingmentioning

confidence: 99%

Artificial Intelligence in Classical and Quantum Photonics

Vernuccio

Bresci

Cimini

et al. 2022

Laser & Photonics Reviews

View full text Add to dashboard Cite

The last decades saw a huge rise of artificial intelligence (AI) as a powerful tool to boost industrial and scientific research in a broad range of fields. AI and photonics are developing a promising two‐way synergy: on the one hand, AI approaches can be used to control a number of complex linear and nonlinear photonic processes, both in the classical and quantum regimes; on the other hand, photonics can pave the way for a new class of platforms to accelerate AI‐tasks. This review provides the reader with the fundamental notions of machine learning (ML) and neural networks (NNs) and presents the main AI applications in the fields of spectroscopy and chemometrics, computational imaging (CI), wavefront shaping and quantum optics. The review concludes with an overview of future developments of the promising synergy between AI and photonics.

show abstract

Section: Photonic Computingmentioning

confidence: 99%

Artificial Intelligence in Classical and Quantum Photonics

Vernuccio

Bresci

Cimini

et al. 2022

Laser & Photonics Reviews

View full text Add to dashboard Cite

show abstract

“…There is a long-standing challenge to implement alloptical ONN training [27], such that the error terms are calculated and backpropagated optically. Our system can be modified to demonstrate an important step towards realising this goal.…”

Section: Optical Calculation Of the Error Vectormentioning

confidence: 99%

Hybrid training of optical neural networks

Spall¹,

Guo²,

Lvovsky³

2022

Preprint

View full text Add to dashboard Cite

Optical neural networks are emerging as a promising type of machine learning hardware capable of energy-efficient, parallel computation. Today's optical neural networks are mainly developed to perform optical inference after in silico training on digital simulators. However, various physical imperfections that cannot be accurately modelled may lead to the notorious "reality gap" between the digital simulator and the physical system. To address this challenge, we demonstrate hybrid training of optical neural networks where the weight matrix is trained with neuron activation functions computed optically via forward propagation through the network. We examine the efficacy of hybrid training with three different networks: an optical linear classifier, a hybrid opto-electronic network, and a complex-valued optical network. We perform a comparative study to in silico training, and our results show that hybrid training is robust against different kinds of static noise. Our platform-agnostic hybrid training scheme can be applied to a wide variety of optical neural networks, and this work paves the way towards advanced all-optical training in machine intelligence.

show abstract

“…There is a long-standing challenge to implement all-optical ONN training [35], such that the error terms are calculated and backpropagated optically. Our system can be modified to demonstrate an important step towards realizing this goal.…”

Section: F Optical Calculation Of the Error Vectormentioning

confidence: 99%