Nonlinear Inference Capacity of Fiber-Optical Extreme Learning Machines
arXiv:2501.18894 · doi:10.1515/nanoph-2025-0045
Abstract
The intrinsic complexity of nonlinear optical phenomena offers a fundamentally new resource to analog brain-inspired computing, with the potential to address the pressing energy requirements of artificial intelligence. We introduce and investigate the concept of nonlinear inference capacity in optical neuromorphic computing in highly nonlinear fiber-based optical Extreme Learning Machines. We demonstrate that this capacity scales with nonlinearity to the point where it surpasses the performance of a deep neural network model with five hidden layers on a scalable nonlinear classification benchmark. By comparing normal and anomalous dispersion fibers under various operating conditions and against digital classifiers, we observe a direct correlation between the system's nonlinear dynamics and its classification performance. Our findings suggest that image recognition tasks, such as MNIST, are incomplete in showcasing deep computing capabilities in analog hardware. Our approach provides a framework for evaluating and comparing computational capabilities, particularly their ability to emulate deep networks, across different physical and digital platforms, paving the way for a more generalized set of benchmarks for unconventional, physics-inspired computing architectures.
14 pages, 6 main figures, 4 appendix figures
References in corpus (8)
- Recent Advances in Physical Reservoir Computing: A Review
- Optoelectronic Reservoir Computing
- All-optical Reservoir Computing
- Single chip photonic deep neural network with accelerated training
- Theory of neuromorphic computing by waves: machine learning by rogue waves, dispersive shocks, and solitons
- Scalable Optical Learning Operator
- Nonlinear optical encoding enabled by recurrent linear scattering
- Principles and Metrics of Extreme Learning Machines Using a Highly Nonlinear Fiber