[HTML][HTML] M3ICRO: Machine learning-enabled compact photonic tensor core based on programmable multi-operand multimode interference
Photonic computing shows promise for transformative advancements in machine learning
(ML) acceleration, offering ultrafast speed, massive parallelism, and high energy efficiency …
(ML) acceleration, offering ultrafast speed, massive parallelism, and high energy efficiency …
Partial coherence boosts photonic computing
H Chen, F Dai - Light: Science & Applications, 2024 - nature.com
The advent of coherent lasers has been a cornerstone of modern optics, with the prevailing
belief that greater coherence always confers an advantage. However, researchers from the …
belief that greater coherence always confers an advantage. However, researchers from the …
Photonic convolutional accelerator operating at Tera-OPs speeds for neural networks with Kerr microcombs
D Moss - Authorea Preprints, 2023 - techrxiv.org
Convolutional neural networks (CNNs), inspired by biological visual cortex systems, are a
powerful category of artificial neural networks that can extract the hierarchical features of raw …
powerful category of artificial neural networks that can extract the hierarchical features of raw …
Physics-based deep learning for modeling nonlinear pulse propagation in optical fibers
A physics-based deep learning (DL) method termed Phynet is proposed for modeling the
nonlinear pulse propagation in optical fibers totally independent of the ground truth. The …
nonlinear pulse propagation in optical fibers totally independent of the ground truth. The …
A review of optical neural networks
D Zhang, Z Tan - Applied Sciences, 2022 - mdpi.com
With the continuous miniaturization of conventional integrated circuits, obstacles such as
excessive cost, increased resistance to electronic motion, and increased energy …
excessive cost, increased resistance to electronic motion, and increased energy …
Lensless opto-electronic neural network with quantum dot nonlinear activation
W Shi, X Jiang, Z Huang, X Li, Y Han, S Yang… - Photonics …, 2024 - opg.optica.org
With the swift advancement of neural networks and their expanding applications in many
fields, optical neural networks have gradually become a feasible alternative to electrical …
fields, optical neural networks have gradually become a feasible alternative to electrical …
Integrated photonic FFT for optical convolutions towards efficient and high-speed neural networks
The technologically-relevant task of feature extraction from data performed in deep-learning
systems is routinely accomplished as repeated fast Fourier transforms (FFT) electronically in …
systems is routinely accomplished as repeated fast Fourier transforms (FFT) electronically in …
Reinforcement learning in a large-scale photonic recurrent neural network
Photonic neural network implementation has been gaining considerable attention as a
potentially disruptive future technology. Demonstrating learning in large-scale neural …
potentially disruptive future technology. Demonstrating learning in large-scale neural …
All-optical photonic integrated neural networks: a first take (Conference Presentation)
M Miscuglio, TT Yu, A Mehrabian… - Ai and optical data …, 2020 - spiedigitallibrary.org
If electro-optic conversion of current photonic NNs could be postponed until the very end of
the network, then the execution time is simply the photon time-of-flight delay. Here we …
the network, then the execution time is simply the photon time-of-flight delay. Here we …
Band-Structure-Engineered Electronic-Photonic Nonlinear Activation Functions
Z Xu, D Burghoff - Physical Review Applied, 2022 - APS
Fast, sensitive, and compact devices that implement nonlinear activation functions are
needed to form fully connected photonic neural networks (PNNs). However, even in highly …
needed to form fully connected photonic neural networks (PNNs). However, even in highly …