Limits of nonlinear and dispersive fiber propagation for an optical fiber-based extreme learning machine
This work addresses the performance limits of optical fiber-based ELMs for machine learning applications, but it is incremental as it focuses on specific propagation effects and noise.
The authors investigated how optical fiber propagation dynamics affect the accuracy of an extreme learning machine (ELM) for the MNIST dataset, achieving test accuracies over 91% and 93% in anomalous and normal dispersion regimes, respectively, and found that quantum noise on input pulses imposes an intrinsic performance penalty.
We report a generalized nonlinear Schrödinger equation simulation model of an extreme learning machine (ELM) based on optical fiber propagation. Using the MNIST handwritten digit dataset as a benchmark, we study how accuracy depends on propagation dynamics, as well as parameters governing spectral encoding, readout, and noise. For this dataset and with quantum noise limited input, test accuracies of : over 91% and 93% are found for propagation in the anomalous and normal dispersion regimes respectively. Our results also suggest that quantum noise on the input pulses introduces an intrinsic penalty to ELM performance.