The effect of choosing optimizer algorithms to improve computer vision tasks: a comparative study

E Hassan, MY Shams, NA Hikal, S Elmougy - Multimedia Tools and …, 2023 - Springer
Optimization algorithms are used to improve model accuracy. The optimization process
undergoes multiple cycles until convergence. A variety of optimization strategies have been …

Large-scale optical reservoir computing for spatiotemporal chaotic systems prediction

M Rafayelyan, J Dong, Y Tan, F Krzakala, S Gigan - Physical Review X, 2020 - APS
Reservoir computing is a relatively recent computational paradigm that originates from a
recurrent neural network and is known for its wide range of implementations using different …

Random features for kernel approximation: A survey on algorithms, theory, and beyond

F Liu, X Huang, Y Chen… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
The class of random features is one of the most popular techniques to speed up kernel
methods in large-scale problems. Related works have been recognized by the NeurIPS Test …

Generalisation error in learning with random features and the hidden manifold model

F Gerace, B Loureiro, F Krzakala… - International …, 2020 - proceedings.mlr.press
We study generalised linear regression and classification for a synthetically generated
dataset encompassing different problems of interest, such as learning with random features …

On-chip bacterial foraging training in silicon photonic circuits for projection-enabled nonlinear classification

G Cong, N Yamamoto, T Inoue, Y Maegami… - Nature …, 2022 - nature.com
On-chip training remains a challenging issue for photonic devices to implement machine
learning algorithms. Most demonstrations only implement inference in photonics for offline …

A review of emerging trends in photonic deep learning accelerators

M Atwany, S Pardo, S Serunjogi, M Rasras - Frontiers in Physics, 2024 - frontiersin.org
Deep learning has revolutionized many sectors of industry and daily life, but as application
scale increases, performing training and inference with large models on massive datasets is …

Large-scale photonic computing with nonlinear disordered media

H Wang, J Hu, A Morandi, A Nardi, F **a, X Li… - Nature Computational …, 2024 - nature.com
Neural networks find widespread use in scientific and technological applications, yet their
implementations in conventional computers have encountered bottlenecks due to ever …

Reservoir computing meets recurrent kernels and structured transforms

J Dong, R Ohana, M Rafayelyan… - Advances in Neural …, 2020 - proceedings.neurips.cc
Reservoir Computing is a class of simple yet efficient Recurrent Neural Networks where
internal weights are fixed at random and only a linear output layer is trained. In the large size …

Photonic Kernel machine learning for ultrafast spectral analysis

Z Denis, I Favero, C Ciuti - Physical Review Applied, 2022 - APS
We introduce photonic kernel machines, a scheme for ultrafast spectral analysis of noisy
radio-frequency signals from single-shot optical intensity measurements. The approach …

Photonic differential privacy with direct feedback alignment

R Ohana, H Medina, J Launay… - Advances in …, 2021 - proceedings.neurips.cc
Abstract Optical Processing Units (OPUs)--low-power photonic chips dedicated to large
scale random projections--have been used in previous work to train deep neural networks …