Reservoir computing with a slowly modulated mask signal for preprocessing using a mutually coupled optoelectronic system

Abstract

Reservoir computing is a machine-learning paradigm based on information processing in the human brain. We numerically demonstrate reservoir computing with a slowly modulated mask signal for preprocessing by using a mutually coupled optoelectronic system. The performance of our system is quantitatively evaluated by a chaotic time series prediction task. Our system can produce comparable performance with reservoir computing with a single feedback system and a fast modulated mask signal. We showed that it is possible to slow down the modulation speed of the mask signal by using the mutually coupled system in reservoir computing.

Numerical Study of Parallel Optoelectronic Reservoir Computing to Enhance Nonlinear Channel Equalization

“…Photonics 2021, 8, x FOR PEER REVIEW 5 of 11 waveform generator) and facilitate the realization of the system, we adopted a slowchanging mask method [17] as a pre-processing method for RC that divides the period into larger parts. Here, the sampling period was divided into N/10 parts so that the duration of each part was 10*θ, and the value of the mask was discrete values of ±1.…”

“…For a fair comparison, the total number of the virtual nodes should be identical between the double-loop and single-loop systems (i.e., N = 150 of a typical RC), and the rest of the parameters set at the best operating point of the respective system. First, we used entropy [17] to compare the internal dynamics of the RC structure, as mentioned above, and the typical single-loop RC. The formula for normalized entropy is as Equation (8), where p i is the probability of the node states being included in the i-th segment.…”

“…As can be seen, the internal dynamics of the double-loop RC were enhanced more than the typical single-loop RC. First, we used entropy [17] to compare the internal dynamics of the RC structure, as mentioned above, and the typical single-loop RC. The formula for normalized entropy is as Equation ( 8), where pi is the probability of the node states being included in the i-th segment.…”

“…A sampling period is divided into N = 50 parts, the duration of each part is θ, and then it is multiplied by a random mask size. To reduce the requirement of the sampling rate of AWG (arbitrary waveform generator) and facilitate the realization of the system, we adopted a slowchanging mask method [17] as a pre-processing method for RC that divides the period into larger parts. Here, the sampling period was divided into N/10 parts so that the duration of each part was 10*θ, and the value of the mask was discrete values of ±1.…”

Effects of Some Operation Parameters on the Performance of a Reservoir Computing System Based on a Delay Feedback Semiconductor Laser With Information Injection by Current Modulation

“…The mask defines the coupling weights between input data and virtual nodes, it is a piecewise constant function with a period T and keeps a constant over an interval θ. To maximize the diversity of virtual node states, the mask is usually constituted by random sequences such as binary mask [25], [26], multi-level mask [27], and chaotic mask [28]. The mask used in this experiment is a binary mask, where the mask values are randomly extracted from {0.1, 1} with equal probability.…”