The role of all-optical neural networks (2306.06632v2)
Abstract: In light of recent achievements in optical computing and machine learning, we consider the conditions under which all-optical computing may surpass electronic and optoelectronic computing in terms of energy efficiency and scalability. When considering the performance of a system as a whole, the cost of memory access and data acquisition is likely to be one of the main efficiency bottlenecks not only for electronic, but also for optoelectronic and all-optical devices. However, we predict that all-optical devices will be at an advantage in the case of inference in large neural network models, and the advantage will be particularly large in the case of generative models. We also consider the limitations of all-optical neural networks including footprint, strength of nonlinearity, optical signal degradation, limited precision of computations, and quantum noise.
- A. Mehonic and A. J. Kenyon, Brain-inspired computing needs a master plan, Nature 604, 255 (2022).
- M. M. Waldrop, The chips are down for moore’s law, Nature News 530, 144 (2016).
- D. A. Miller, Attojoule optoelectronics for low-energy information processing and communications, Journal of Lightwave Technology 35, 346 (2017).
- J. Misra and I. Saha, Artificial neural networks in hardware: A survey of two decades of progress, Neurocomputing 74, 239 (2010).
- N. Stroev and N. G. Berloff, Renaissance of analogue optical computing, arXiv preprint arXiv:2301.11760 (2023).
- D. A. B. Miller, Are optical transistors the logical next step?, Nature Photonics 4, 3 (2010a).
- F. Ashtiani, A. J. Geers, and F. Aflatouni, An on-chip photonic deep neural network for image classification, Nature 606, 501 (2022).
- D. A. B. Miller, Optical interconnects to electronic chips, Appl. Opt. 49, F59 (2010b).
- A. N. Tait, Quantifying power in silicon photonic neural networks, Physical Review Applied 17, 054029 (2022).
- J. A. Barrachina, Negu93/cvnn: Complex-valued neural networks (2022).
- J. Spall, X. Guo, and A. I. Lvovsky, Hybrid training of optical neural networks, Optica 9, 803 (2022).
- Y. Arakawa and M. J. Holmes, Progress in quantum-dot single photon sources for quantum information technologies: A broad spectrum overview, Applied Physics Reviews 7, 021309 (2020).
- H. W. Lin, M. Tegmark, and D. Rolnick, Why does deep and cheap learning work so well?, Journal of Statistical Physics 168, 1223 (2017).
- J. W. Goodman, Fan-in and fan-out with optical interconnections, Optica Acta: International Journal of Optics 32, 1489 (1985), https://doi.org/10.1080/713821684 .