# Scalable Optical Learning Operator

arXiv: https://arxiv.org/abs/2012.12404 · HTML: https://mlsanity.com/paper/2012.12404/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2020.

## Built on by (most cited first, 19 of 19)

- [Training of Physical Neural Networks](https://mlsanity.com/paper/2406.03372/) (2024)
- [Backpropagation-free Training of Deep Physical Neural Networks](https://mlsanity.com/paper/2304.11042/) (2023)
- [Nonlinear Processing with Linear Optics](https://mlsanity.com/paper/2307.08533/) (2023)
- [Forward-Forward Training of an Optical Neural Network](https://mlsanity.com/paper/2305.19170/) (2023)
- [Nonlinear optical encoding enabled by recurrent linear scattering](https://mlsanity.com/paper/2307.08558/) (2023)
- [Spatially Varying Nanophotonic Neural Networks](https://mlsanity.com/paper/2308.03407/) (2023)
- [Polarization Multiplexed Diffractive Computing: All-Optical Implementation of a Group of Linear Transformations Through a Polarization-Encoded Diffractive Network](https://mlsanity.com/paper/2203.13482/) (2022)
- [Arbitrary control over multimode wave propagation for machine learning](https://mlsanity.com/paper/2402.17750/) (2024)
- [Wave-based extreme deep learning based on non-linear time-Floquet entanglement](https://mlsanity.com/paper/2107.08564/) (2021)
- [Parallel photonic accelerator for decision making using optical spatiotemporal chaos](https://mlsanity.com/paper/2210.06976/) (2022)
- [Deep Optical Coding Design in Computational Imaging](https://mlsanity.com/paper/2207.00164/) (2022)
- [Nonlinear Optical Data Transformer for Machine Learning](https://mlsanity.com/paper/2208.09398/) (2022)
- [Multiplexed all-optical permutation operations using a reconfigurable diffractive optical network](https://mlsanity.com/paper/2402.02397/) (2024)
- [Physical Foundation Models: Fixed hardware implementations of large-scale neural networks](https://mlsanity.com/paper/2604.27911/) (2026)
- [Low-power multi-mode fiber projector overcomes shallow neural networks classifiers](https://mlsanity.com/paper/2210.04745/) (2022)
- [Scientific Computing with Diffractive Optical Neural Networks](https://mlsanity.com/paper/2302.10905/) (2023)
- [Training Hybrid Neural Networks with Multimode Optical Nonlinearities Using Digital Twins](https://mlsanity.com/paper/2501.07991/) (2025)
- [Integrated Computation and Communication with Fiber-optic Transmissions](https://mlsanity.com/paper/2503.02165/) (2025)
- [On-chip wave chaos for photonic extreme learning](https://mlsanity.com/paper/2508.19878/) (2025)

## Abstract (arXiv)

Today's heavy machine learning tasks are fueled by large datasets. Computing is performed with power hungry processors whose performance is ultimately limited by the data transfer to and from memory. Optics is one of the powerful means of communicating and processing information and there is intense current interest in optical information processing for realizing high-speed computations. Here we present and experimentally demonstrate an optical computing framework based on spatiotemporal effects in multimode fibers for a range of learning tasks from classifying COVID-19 X-ray lung images and speech recognition to predicting age from face images. The presented framework overcomes the energy scaling problem of existing systems without compromising speed. We leveraged simultaneous, linear, and nonlinear interaction of spatial modes as a computation engine. We numerically and experimentally showed the ability of the method to execute several different tasks with accuracy comparable to a digital implementation.