English

Hardware-In-The-Loop Training of a 4f Optical Correlator with Logarithmic Complexity Reduction for CNNs

Neural and Evolutionary Computing 2025-01-09 v1
Authors: Lorenzo Pes , Maryam Dehbashizadeh Chehreghan , Rick Luiken , Sander Stuijk , Ripalta Stabile , Federico Corradi
View on arXiv ↗ PDF ↗

Abstract

This work evaluates a forward-only learning algorithm on the MNIST dataset with hardware-in-the-loop training of a 4f optical correlator, achieving 87.6% accuracy with O(n2) complexity, compared to backpropagation, which achieves 88.8% accuracy with O(n2 log n) complexity.

Keywords

hardware-in-the-loop optical correlator CNN logarithmic complexity MNIST

Cite

@article{arxiv.2501.04141,
  title  = {Hardware-In-The-Loop Training of a 4f Optical Correlator with Logarithmic Complexity Reduction for CNNs},
  author = {Lorenzo Pes and Maryam Dehbashizadeh Chehreghan and Rick Luiken and Sander Stuijk and Ripalta Stabile and Federico Corradi},
  journal= {arXiv preprint arXiv:2501.04141},
  year   = {2025}
}

Related papers

View all related →
Optics · Physics
Misaligned orientations of 4f optical neural network for image classification accuracy on various datasets
Yanbing Liu, Wei Li, Kun Cheng, Xun Liu +1
2022-10-18
Emerging Technologies · Computer Science
Forward-only learning in memristor arrays with month-scale stability
Adrien Renaudineau, Mamadou Hawa Diallo, Théo Dupuis, Bastien Imbert +11
2026-03-05
Machine Learning · Computer Science
Training a neural network with exciton-polariton optical nonlinearity
Andrzej Opala, Riccardo Panico, Vincenzo Ardizzone, Barbara Pietka +4
2022-06-16
Emerging Technologies · Computer Science
High speed and reconfigurable optronic neural network with digital nonlinear activation
Qiuhao Wu, Jia Liu, Xiubao Sui, Liping Wang +1
2021-10-13
Distributed, Parallel, and Cluster Computing · Computer Science
Exploring Parallelism in FPGA-Based Accelerators for Machine Learning Applications
Sed Centeno, Christopher Sprague, Arnab A Purkayastha, Ray Simar +1
2025-11-18
Machine Learning · Computer Science
Forward Only Learning for Orthogonal Neural Networks of any Depth
Paul Caillon, Alex Colagrande, Erwan Fagnou, Blaise Delattre +1
2025-12-25
Machine Learning · Computer Science
Light-in-the-loop: using a photonics co-processor for scalable training of neural networks
Julien Launay, Iacopo Poli, Kilian Müller, Igor Carron +3
2020-06-04
Machine Learning · Computer Science
LILogic Net: Compact Logic Gate Networks with Learnable Connectivity for Efficient Hardware Deployment
Katarzyna Fojcik, Renaldas Zioma, Jogundas Armaitis
2026-04-28
Neural and Evolutionary Computing · Computer Science
Hardware-efficient on-line learning through pipelined truncated-error backpropagation in binary-state networks
Hesham Mostafa, Bruno Pedroni, Sadique Sheik, Gert Cauwenberghs
2017-08-17
Computer Vision and Pattern Recognition · Computer Science
Neural Tangent Knowledge Distillation for Optical Convolutional Networks
Jinlin Xiang, Minho Choi, Yubo Zhang, Zhihao Zhou +2
2025-08-13
Optics · Physics
Training neural networks with end-to-end optical backpropagation
James Spall, Xianxin Guo, A. I. Lvovsky
2025-02-07
Emerging Technologies · Computer Science
Learning in Memristive Neural Network Architectures using Analog Backpropagation Circuits
Olga Krestinskaya, Khaled Nabil Salama, Alex Pappachen James
2018-09-03
Machine Learning · Computer Science
Forward-Forward Training of an Optical Neural Network
Ilker Oguz, Junjie Ke, Qifei Wang, Feng Yang +5
2023-08-11
Emerging Technologies · Computer Science
Streamlined optical training of large-scale modern deep learning architectures with direct feedback alignment
Ziao Wang, Kilian Müller, Matthew Filipovich, Julien Launay +11
2025-04-03
Optics · Physics
Nonlinear Optical Joint Transform Correlator for Low Latency Convolution Operations
Jonathan K. George, Maria Solyanik-Gorgone, Hangbo Yang, Chee Wei Wong +1
2022-06-15
Emerging Technologies · Computer Science
Low-power scalable multilayer optoelectronic neural networks enabled with incoherent light
Alexander Song, Sai Nikhilesh Murty Kottapalli, Rahul Goyal, Bernhard Schölkopf +1
2024-02-06
Neural and Evolutionary Computing · Computer Science
Very Efficient Training of Convolutional Neural Networks using Fast Fourier Transform and Overlap-and-Add
Tyler Highlander, Andres Rodriguez
2016-01-27
Machine Learning · Computer Science
Automatic Compiler Based FPGA Accelerator for CNN Training
Shreyas Kolala Venkataramanaiah, Yufei Ma, Shihui Yin, Eriko Nurvithadhi +3
2019-08-20
Machine Learning · Computer Science
Efficient Deep Learning with Decorrelated Backpropagation
Sander Dalm, Joshua Offergeld, Nasir Ahmad, Marcel van Gerven
2025-11-12
Optics · Physics
Optical convolutional neural network with atomic nonlinearity
Mingwei Yang, Elizabeth Robertson, Luisa Esguerra, Kurt Busch +1
2023-05-17
Machine Learning · Computer Science
LOT: Layer-wise Orthogonal Training on Improving $\ell_2$ Certified Robustness
Xiaojun Xu, Linyi Li, Bo Li
2023-03-28
Machine Learning · Computer Science
FFCL: Forward-Forward Net with Cortical Loops, Training and Inference on Edge Without Backpropagation
Ali Karkehabadi, Houman Homayoun, Avesta Sasan
2024-05-22
Neural and Evolutionary Computing · Computer Science
Classification Accuracy Improvement for Neuromorphic Computing Systems with One-level Precision Synapses
Yandan Wang, Wei Wen, Linghao Song, Hai Li
2017-01-10
Machine Learning · Computer Science
Advancing On-Device Neural Network Training with TinyPropv2: Dynamic, Sparse, and Efficient Backpropagation
Marcus Rüb, Axel Sikora, Daniel Mueller-Gritschneder
2024-09-12
Machine Learning · Computer Science
Training all-mechanical neural networks for task learning through in situ backpropagation
Shuaifeng Li, Xiaoming Mao
2024-04-25