Reservoir Computing based on Mutually Injected Phase Modulated Lasers: A monolithic integration approach suitable for short-reach communication systems
1
Citation
4
Reference
10
Related Paper
Citation Trend
Abstract:
We propose a reservoir computing system consisting of two mutually coupled phase modulated lasers. The scheme can be monolithic integrated and extends the reach of 25Gbaud PAM-4 signals up to 55 km in the C-band.Keywords:
Reservoir computing
Reservoir computing is a machine learning model that is widely used for time series tasks due to its advantages of low cost and fast learning. However, conventional reservoir computing often do not achieve the memory capacity and nonlinearity required for the task. To solve this problem, we proposed hysteresis reservoir computing which conventional reservoir neurons are replaced by hysteresis neurons. The model generates various output sequences by changing their parameters. In addition, it has the potential to memorize time series because it presents complex periodic solutions. In this paper, we confirm the dynamics generated by changing the hysteresis reservoir computing parameters. The experimental results show that changing the parameters improves the learning ability and can represent specific series of data. This indicates an important dynamics in terms of memory capacity and the ability to represent.
Reservoir computing
Hysteresis
Memorization
Cite
Citations (2)
Forecasting chaotic systems is a notably complex task, which in recent years has been approached with reasonable success using reservoir computing (RC), a recurrent network with fixed random weights (the reservoir) used to extract the spatio-temporal information of the system. This work presents a hybrid quantum reservoir-computing (HQRC) framework, which replaces the reservoir in RC with a quantum circuit. The modular structure and measurement feedback in the circuit are used to encode the complex system dynamics in the reservoir states, from which classical learning is performed to predict future dynamics. The noiseless simulations of HQRC demonstrate valid prediction times comparable to state-of-the-art classical RC models for both the Lorenz63 and double-scroll chaotic paradigmatic systems and adhere to the attractor dynamics long after the forecasts have deviated from the ground truth.
Reservoir computing
ENCODE
Cite
Citations (2)
Photonic reservoir computing is a promising candidate for low-energy computing at high bandwidths. Despite recent successes, there are bounds to what one can achieve simply by making photonic reservoirs larger. Therefore, a switch from single-reservoir computing to multi-reservoir and even deep physical reservoir computing is desirable. Given that backpropagation can not be used directly to train multi-reservoir systems in our targeted setting, we propose an alternative approach that still uses its power to derive intermediate targets. In this work we report our findings on a conducted experiment to evaluate the general feasibility of our approach by training a network of 3 Echo State Networks to perform the well-known NARMA-10 task using targets derived through backpropagation. Our results indicate that our proposed method is well-suited to train multi-reservoir systems in a efficient way.
Reservoir computing
Backpropagation
Cite
Citations (2)
The concept of reservoir computing emerged from a specific machine learning paradigm characterized by a three-layered architecture (input, reservoir, and output), where only the output layer is trained and optimized for a particular task. In recent years, this approach has been successfully implemented using various hardware platforms based on optoelectronic and photonic systems with time-delayed feedback. In this review, we provide a survey of the latest advances in this field, with some perspectives related to the relationship between reservoir computing, nonlinear dynamics, and network theory.
Reservoir computing
Cite
Citations (74)
Physical reservoir computing is a computational paradigm that enables temporal pattern recognition to be performed directly in physical matter. By exciting non-linear dynamical systems and linearly classifying their changes in state, we can create highly energy-efficient devices capable of solving machine learning tasks without the need to build a modular system consisting of millions of neurons interconnected by synapses. The chosen dynamical system must have three desirable properties: non-linearity, complexity, and fading memory to act as an effective reservoir. We present task agnostic quantitative measures for each of these three requirements and exemplify them for two reservoirs: an echo state network and a simulated magnetic skyrmion-based reservoir. We show that, in general, systems with lower damping reach higher values in all three performance metrics. Whilst for input signal strength, there is a natural trade-off between memory capacity and non-linearity of the reservoir's behaviour. In contrast to typical task-dependent reservoir computing benchmarks, these metrics can be evaluated in parallel from a single input signal, drastically speeding up the parameter search to design efficient and high-performance reservoirs.
Reservoir computing
Linearity
SIGNAL (programming language)
Echo state network
Cite
Citations (0)
Reservoir computing is a computational framework suited for temporal/sequential data processing. It is derived from several recurrent neural network models, including echo state networks and liquid state machines. A reservoir computing system consists of a reservoir for mapping inputs into a high-dimensional space and a readout for pattern analysis from the high-dimensional states in the reservoir. The reservoir is fixed and only the readout is trained with a simple method such as linear regression and classification. Thus, the major advantage of reservoir computing compared to other recurrent neural networks is fast learning, resulting in low training cost. Another advantage is that the reservoir without adaptive updating is amenable to hardware implementation using a variety of physical systems, substrates, and devices. In fact, such physical reservoir computing has attracted increasing attention in diverse fields of research. The purpose of this review is to provide an overview of recent advances in physical reservoir computing by classifying them according to the type of the reservoir. We discuss the current issues and perspectives related to physical reservoir computing, in order to further expand its practical applications and develop next-generation machine learning systems.
Reservoir computing
Echo state network
Cite
Citations (1,431)
Aiming at the difficulties of mine communication,a scheme of mine through-the-earth(communication) system using spread-spectrum technology was proposed,which can be realized digitally.And the(theoretical) analysis and whole simulation of this scheme were carried out.The results demons-(trated) that this scheme was practicable and effective,which was fundamental to design the communication system.
Digitization
Cite
Citations (1)
We propose a novel molecular computing approach based on reservoir computing. In reservoir computing, a dynamical core, called a reservoir, is perturbed with an external input signal while a readout layer maps the reservoir dynamics to a target output. Computation takes place as a transformation from the input space to a high-dimensional spatiotemporal feature space created by the transient dynamics of the reservoir. The readout layer then combines these features to produce the target output. We show that coupled deoxyribozyme oscillators can act as the reservoir. We show that despite using only three coupled oscillators, a molecular reservoir computer could achieve 90% accuracy on a benchmark temporal problem.
Reservoir computing
Benchmark (surveying)
DNA Computing
Transient (computer programming)
Cite
Citations (0)
Reservoir computing
Representation
Echo state network
Cite
Citations (0)
We propose a novel molecular computing approach based on reservoir computing. In reservoir computing, a dynamical core, called a reservoir, is perturbed with an external input signal while a readout layer maps the reservoir dynamics to a target output. Computation takes place as a transformation from the input space to a high-dimensional spatiotemporal feature space created by the transient dynamics of the reservoir. The readout layer then combines these features to produce the target output. We show that coupled deoxyribozyme oscillators can act as the reservoir. We show that despite using only three coupled oscillators, a molecular reservoir computer could achieve 90% accuracy on a benchmark temporal problem.
Reservoir computing
Benchmark (surveying)
DNA Computing
Transient (computer programming)
Cite
Citations (3)