Photonic Nonlinear Transient Computing with Multiple-Delay Wavelength Dynamics

We report on the experimental demonstration of a hybrid optoelectronic neuromorphic computer based on a complex nonlinear wavelength dynamics including multiple delayed feedbacks with randomly defined weights. This neuromorphic approach is based on a new paradigm of a brain-inspired computational unit, intrinsically differing from Turing machines. This recent paradigm consists in expanding the input information to be processed into a higher dimensional phase space, through the nonlinear transient response of a complex dynamics excited by the input information. The computed output is then extracted via a linear separation of the transient trajectory in the complex phase space. The hyperplane separation is derived from a learning phase consisting of the resolution of a regression problem. The processing capability originates from the nonlinear transient, resulting in nonlinear transient computing. The computational performance is successfully evaluated on a standard benchmark test, namely, a spoken digit recognition task.

Figure 1

Principles of an NTC. (a) With a spatially extended dynamical network. (b) With multiple delay feedback dynamics.

Figure 2

Optoelectronic wavelength setup performing an NTC as multiple-delay feedback dynamics.

Figure 3

Illustration of the NTC processing on the spoken digits; example of the spatiotemporal representation for the digit “seven.”

Figure 4

Experimental results. Left: Transfer functions for 15 (red, thinner line) and 150 (black, thicker line) delayed feedbacks with random weights (theoretical curves in full lines, experimental data in symbols). Right: WER histograms with 15 delayed feedbacks and a total of 120 cross validations.