Photonic Extreme Learning Machine based on frequency multiplexing
arXiv:2107.04585 · doi:10.1364/OE.433535
Abstract
The optical domain is a promising field for physical implementation of neural networks, due to the speed and parallelism of optics. Extreme Learning Machines (ELMs) are feed-forward neural networks in which only output weights are trained, while internal connections are randomly selected and left untrained. Here we report on a photonic ELM based on a frequency-multiplexed fiber setup. Multiplication by output weights can be performed either offline on a computer, or optically by a programmable spectral filter. We present both numerical simulations and experimental results on classification tasks and a nonlinear channel equalization task.
arXiv comment22 pages, 16 figures
References in corpus (13)
- All-Optical Machine Learning Using Diffractive Deep Neural Networks
- Parallel convolution processing using an integrated photonic tensor core
- 11 TeraFLOPs per second photonic convolutional accelerator for deep learning optical neural networks
- Optoelectronic Reservoir Computing
- Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit
- All-optical Reservoir Computing
- Microwave and RF signal processing based on integrated soliton crystal optical microcombs
- High performance photonic reservoir computer based on a coherently driven passive cavity
- Theory of neuromorphic computing by waves: machine learning by rogue waves, dispersive shocks, and solitons
- Frequency Bin Entangled Photons
- Random Projections through multiple optical scattering: Approximating kernels at the speed of light
- Photonic extreme learning machine by free-space optical propagation
- Approximation Bounds for Random Neural Networks and Reservoir Systems
Cited by in corpus (6)
- Photonic neural networks based on integrated silicon microresonators
- Deep Photonic Reservoir Computer Based on Frequency Multiplexing with Fully Analog Connection Between Layers
- Photonic reservoir computer based on frequency multiplexing
- An array of microresonators as a Photonic Extreme Learning Machine
- Optical neuromorphic computing via temporal up-sampling and trainable encoding on a telecom device platform
- Shannon Entropy Helps Optimize the Performance of a Frequency-Multiplexed Extreme Learning Machine