# Dual adaptive training of photonic neural networks

arXiv: https://arxiv.org/abs/2212.06141 · HTML: https://mlsanity.com/paper/2212.06141/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 56 references that are in the map.
- First posted on arXiv 9 Dec 2022.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [Deep Complex Networks](https://mlsanity.com/paper/1705.09792/) (2017)
- [All-Optical Machine Learning Using Diffractive Deep Neural Networks](https://mlsanity.com/paper/1804.08711/) (2018)
- [Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems](https://mlsanity.com/paper/2104.13386/) (2021)
- [Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit](https://mlsanity.com/paper/2008.11659/) (2020)
- [Training of photonic neural networks through in situ backpropagation](https://mlsanity.com/paper/1805.09943/) (2018)
- [Wave Physics as an Analog Recurrent Neural Network](https://mlsanity.com/paper/1904.12831/) (2019)
- [Reinforcement Learning in a large scale photonic Recurrent Neural Network](https://mlsanity.com/paper/1711.05133/) (2017)
- [Massively Parallel Amplitude-Only Fourier Neural Network](https://mlsanity.com/paper/2008.05853/) (2020)
- [L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization](https://mlsanity.com/paper/2110.14807/) (2021)
- [Reprogrammable Electro-Optic Nonlinear Activation Functions for Optical Neural Networks](https://mlsanity.com/paper/1903.04579/) (2019)
- [Silicon Photonic Architecture for Training Deep Neural Networks with Direct Feedback Alignment](https://mlsanity.com/paper/2111.06862/) (2021)
- [Hybrid training of optical neural networks](https://mlsanity.com/paper/2203.11207/) (2022)
- [Superconducting optoelectronic circuits for neuromorphic computing](https://mlsanity.com/paper/1610.00053/) (2016)
- [Matrix optimization on universal unitary photonic devices](https://mlsanity.com/paper/1808.00458/) (2018)

## Built on by (most cited first, 9 of 9)

- [Asymmetrical estimator for training encapsulated deep photonic neural networks](https://mlsanity.com/paper/2405.18458/) (2024)
- [Super-resolution imaging using super-oscillatory diffractive neural networks](https://mlsanity.com/paper/2406.19126/) (2024)
- [Neural Tangent Knowledge Distillation for Optical Convolutional Networks](https://mlsanity.com/paper/2508.08421/) (2025)
- [Low-rank surrogate modeling and stochastic zero-order optimization for training of neural networks with black-box layers](https://mlsanity.com/paper/2509.15113/) (2025)
- [Compute-first optical detection for noise-resilient visual perception](https://mlsanity.com/paper/2403.09612/) (2024)
- [Meta-training of diffractive meta-neural networks for super-resolution direction of arrival estimation](https://mlsanity.com/paper/2509.05926/) (2025)
- [Training single-electron and single-photon stochastic physical neural networks](https://mlsanity.com/paper/2604.10861/) (2026)
- [Inverse-designed meta processing units for multi-task near-field photonic computing](https://mlsanity.com/paper/2607.08360/) (2026)
- [LCAP: Population-Informed Latent Chip Adaptation from Few Output Probes for Photonic Neural Networks](https://mlsanity.com/paper/2609.16823/) (2026)

## Abstract (arXiv)

Photonic neural network (PNN) is a remarkable analog artificial intelligence (AI) accelerator that computes with photons instead of electrons to feature low latency, high energy efficiency, and high parallelism. However, the existing training approaches cannot address the extensive accumulation of systematic errors in large-scale PNNs, resulting in a significant decrease in model performance in physical systems. Here, we propose dual adaptive training (DAT) that allows the PNN model to adapt to substantial systematic errors and preserves its performance during the deployment. By introducing the systematic error prediction networks with task-similarity joint optimization, DAT achieves the high similarity mapping between the PNN numerical models and physical systems and high-accurate gradient calculations during the dual backpropagation training. We validated the effectiveness of DAT by using diffractive PNNs and interference-based PNNs on image classification tasks. DAT successfully trained large-scale PNNs under major systematic errors and preserved the model classification accuracies comparable to error-free systems. The results further demonstrated its superior performance over the state-of-the-art in situ training approaches. DAT provides critical support for constructing large-scale PNNs to achieve advanced architectures and can be generalized to other types of AI systems with analog computing errors.