# Massively Parallel Amplitude-Only Fourier Neural Network

arXiv: https://arxiv.org/abs/2008.05853 · HTML: https://mlsanity.com/paper/2008.05853/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2020.

## Built on by (most cited first, 21 of 21)

- [An optical neural network using less than 1 photon per multiplication](https://mlsanity.com/paper/2104.13467/) (2021)
- [All-Optical Synthesis of an Arbitrary Linear Transformation Using Diffractive Surfaces](https://mlsanity.com/paper/2108.09833/) (2021)
- [L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization](https://mlsanity.com/paper/2110.14807/) (2021)
- [Hybrid training of optical neural networks](https://mlsanity.com/paper/2203.11207/) (2022)
- [A compact butterfly-style silicon photonic-electronic neural chip for hardware-efficient deep learning](https://mlsanity.com/paper/2111.06705/) (2021)
- [Single-Shot Optical Neural Network](https://mlsanity.com/paper/2205.09103/) (2022)
- [Optical Transformers](https://mlsanity.com/paper/2302.10360/) (2023)
- [Dual adaptive training of photonic neural networks](https://mlsanity.com/paper/2212.06141/) (2022)
- [Quantum-limited stochastic optical neural networks operating at a few quanta per activation](https://mlsanity.com/paper/2307.15712/) (2023)
- [Intelligent Computing: The Latest Advances, Challenges and Future](https://mlsanity.com/paper/2211.11281/) (2022)
- [FatNet: High Resolution Kernels for Classification Using Fully Convolutional Optical Neural Networks](https://mlsanity.com/paper/2210.16914/) (2022)
- [EEG Opto-processor: epileptic seizure detection using diffractive photonic computing units](https://mlsanity.com/paper/2301.10167/) (2022)
- [Hardware-Efficient Photonic Tensor Core: Accelerating Deep Neural Networks with Structured Compression](https://mlsanity.com/paper/2502.01670/) (2025)
- [High Throughput Multi-Channel Parallelized Diffraction Convolutional Neural Network Accelerator](https://mlsanity.com/paper/2112.12297/) (2021)
- [PhotoFourier: A Photonic Joint Transform Correlator-Based Neural Network Accelerator](https://mlsanity.com/paper/2211.05276/) (2022)
- [Misaligned orientations of 4f optical neural network for image classification accuracy on various datasets](https://mlsanity.com/paper/2210.08004/) (2022)
- [QuATON: Quantization Aware Training of Optical Neurons](https://mlsanity.com/paper/2310.03049/) (2023)
- [Hyperspectral In-Memory Computing with Optical Frequency Combs and Programmable Optical Memories](https://mlsanity.com/paper/2310.11014/) (2023)
- [1-bit Quantized On-chip Hybrid Diffraction Neural Network Enabled by Authentic All-optical Fully-connected Architecture](https://mlsanity.com/paper/2404.07443/) (2024)
- [Metasurface-generated large and arbitrary analog convolution kernels for accelerated machine vision](https://mlsanity.com/paper/2409.18614/) (2024)
- [ConvShareViT: Enhancing Vision Transformers with Convolutional Attention Mechanisms for Free-Space Optical Accelerators](https://mlsanity.com/paper/2504.11517/) (2025)

## Abstract (arXiv)

Machine-intelligence has become a driving factor in modern society. However, its demand outpaces the underlying electronic technology due to limitations given by fundamental physics such as capacitive charging of wires, but also by system architecture of storing and handling data, both driving recent trends towards processor heterogeneity. Here we introduce a novel amplitude-only Fourier-optical processor paradigm capable of processing large-scale ~(1,000 x 1,000) matrices in a single time-step and 100 microsecond-short latency. Conceptually, the information-flow direction is orthogonal to the two-dimensional programmable-network, which leverages 10^6-parallel channels of display technology, and enables a prototype demonstration performing convolutions as pixel-wise multiplications in the Fourier domain reaching peta operations per second throughputs. The required real-to-Fourier domain transformations are performed passively by optical lenses at zero-static power. We exemplary realize a convolutional neural network (CNN) performing classification tasks on 2-Megapixel large matrices at 10 kHz rates, which latency-outperforms current GPU and phase-based display technology by one and two orders of magnitude, respectively. Training this optical convolutional layer on image classification tasks and utilizing it in a hybrid optical-electronic CNN, shows classification accuracy of 98% (MNIST) and 54% (CIFAR-10). Interestingly, the amplitude-only CNN is inherently robust against coherence noise in contrast to phase-based paradigms and features an over 2 orders of magnitude lower delay than liquid crystal-based systems. Beyond contributing to novel accelerator technology, scientifically this amplitude-only massively-parallel optical compute-paradigm can be far-reaching as it de-validates the assumption that phase-information outweighs amplitude in optical processors for machine-intelligence.