# Photonic Delay Systems as Machine Learning Implementations

arXiv: https://arxiv.org/abs/1501.02592 · HTML: https://mlsanity.com/paper/1501.02592/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jan 2015.

## Built on by (most cited first, 5 of 5)

- [Self-learning Machines based on Hamiltonian Echo Backpropagation](https://mlsanity.com/paper/2103.04992/) (2021)
- [Asymptotic Stability in Reservoir Computing](https://mlsanity.com/paper/2206.03854/) (2022)
- [Silicon Photonic Microring Based Chip-Scale Accelerator for Delayed Feedback Reservoir Computing](https://mlsanity.com/paper/2101.00557/) (2021)
- [Blending Optimal Control and Biologically Plausible Learning for Noise-Robust Physical Neural Networks](https://mlsanity.com/paper/2502.19053/) (2025)
- [Reservoir Computers Modal Decomposition and Optimization](https://mlsanity.com/paper/2101.07219/) (2021)

## Abstract (arXiv)

Nonlinear photonic delay systems present interesting implementation platforms for machine learning models. They can be extremely fast, offer great degrees of parallelism and potentially consume far less power than digital processors. So far they have been successfully employed for signal processing using the Reservoir Computing paradigm. In this paper we show that their range of applicability can be greatly extended if we use gradient descent with backpropagation through time on a model of the system to optimize the input encoding of such systems. We perform physical experiments that demonstrate that the obtained input encodings work well in reality, and we show that optimized systems perform significantly better than the common Reservoir Computing approach. The results presented here demonstrate that common gradient descent techniques from machine learning may well be applicable on physical neuro-inspired analog computers.