**Chapter 5**

*Advances and Applications in Deep Learning*

[16] Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial with nonlinear activation functions. Optica. 2019;**6**:1132-1137. DOI: 10.1364/

Prabhu M, Baehhr-Jones T, Hochberg M, et al. Deep Learning with Coherent Nanophotonic Circuits. 2016.

[26] Hughes T, Minkov M, Shi Y, Fan S. Training of photonic neural networks through in situ backpropagation and gradient measurement. Optica. 2018;**5**:864-871. DOI: 10.1364/

[27] Zhang T, Wang J, Dan Y, Lanqiu Y, Dai J, Han X, et al. Efficient training and design of photonic neural network through neuroevolution. Optics Express. 2018;**27**:37150-37163. DOI: 10.1364/

Amin R, Meng J, Lima T, Tait A, et al. Neuromorphic photonics with electroabsorption modulators. Optics Express. 2019;**27**:5181-5191. DOI: 10.1364/

[29] Denz C. Optical Neural Networks. New York: Springer; 1998. DOI: 10.1007/978-3-663-12272-2

[30] Feldmann J, Youngblood N, Wright C, Bhaskaran, Pernice W. Alloptical spiking neurosynaptic networks with self-learning capabilities. Nature. 2019;**569**:208-214. DOI: 10.1038/

[31] Tait A, Lima T, Nahmias M,

Miller H, Peng H, Shastri B, et al. Silicon photonic modulator neuron. Physical Review Applied. 2019;**11**:064043. DOI: 10.1103/PhysRevApplied.11.064043

[25] Shen Y, Harris N, Skirlo S,

OPTICA.6.001132

arXiv:1610.02365

OPTICA.5.000864

OE.27.037150

OE.27.005181

s41586-019-1157-8

[28] George J, Mehrabian A,

International Conference on Neural Information Processing Systems (NIPS 2014); Montréal, Canada; 8-13 December, 2014. pp. 2672-2680

nets. In: Proceedings of the

[17] An S, Zheng B, Tang H, Shalaginov M, Zhou L, Li H, et al. Generative Multi-Functional Meta-Atom and Metasurface Design Networks. arXiv:1908.04851

[18] Jiang J, Sell D, Hoyer S, Hickey J, Yang J, Fan J. Free-form diffractive metagrating design based on generative adversarial networks. ACS Nano. 2019;**13**:8872-8878. DOI: 10.1021/

[19] Jiang J, Fan J. Global optimisation of dielectric metasurfaces using a physicsdriven neural network. Nano Letters. 2019;**19**:5366-5372. DOI: 10.1021/acs.

[20] Jiang J, Fan J. Simulator-based training of generative neural networks for the inverse design of metasurfaces. Nanophotonics. 2020;**9**:1059-1069. DOI:

Deep-learning-enabled on-demand design of chiral metamaterials. ACS Nano. 2018;**12**:6326-6334. DOI: 10.1021/

[22] Li Y, Xu Y, Jiang M, Li B, Han T, Chi C, et al. Generative model for the inverse design of metasurfaces. Physical Review Letters. 2019;**123**:213902. DOI: 10.1103/PhysRevLett.123.213902

[23] Sui X, Wu Q, Liu J, Chen Q, Gu G. A review of optical neural networks. IEEE Access. 2020;**8**:70773-70783. DOI:

[24] Zuo Y, Li B, Zhao Y, Jiang Y, Chen Y, Chen P, et al. All-optical neural network

10.1109/ACCESS.2020.2987333

10.1515/nanoph-2019-0330

[21] Ma W, Cheng F, Liu Y.

acsnano.9b02371

nanolett.9b01857

acsnano.8b03569

**78**
