paper-with-me

홈 › Papers

Optimizing Memory in Reservoir Computers

2022-01-05 · Thomas L. Carroll

A reservoir computer is a way of using a high dimensional dynamical system for computation. One way to construct a reservoir computer is by connecting a set of nonlinear nodes into a network. Because the network creates feedback between nodes, the reservoir computer has memory. If the reservoir computer is to respond to an input signal in a consistent way (a necessary condition for computation), the memory must be fading; that is, the influence of the initial conditions fades over time. How long this memory lasts is important for determining how well the reservoir computer can solve a particular problem. In this paper I describe ways to vary the length of the fading memory in reservoir computers. Tuning the memory can be important to achieve optimal results in some problems; too much or too little memory degrades the accuracy of the computation.

📄 PDF Abstract BibTeX arXiv:2201.01605

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Forecasting Chaotic Systems with Very Low Connectivity Reservoir Computers

2019-10-01 · Aaron Griffith, Andrew Pomerance, Daniel J. Gauthier

We explore the hyperparameter space of reservoir computers used for forecasting of the chaotic Lorenz '63 attractor with Bayesian optimization. We use a new measure of reservoir performance, designed to emphasize learnin…

Bayesian Optimization

Master memory function for delay-based reservoir computers with single-variable dynamics

2021-08-28 · Felix Köster, Serhiy Yanchuk, Kathy Lüdge

We show that many delay-based reservoir computers considered in the literature can be characterized by a universal master memory function (MMF). Once computed for two independent parameters, this function provides linear…

Time Shifts to Reduce the Size of Reservoir Computers

2022-05-03 · Thomas L. Carroll, Joseph D. Hart

A reservoir computer is a type of dynamical system arranged to do computation. Typically, a reservoir computer is constructed by connecting a large number of nonlinear nodes in a network that includes recurrent connectio…

Universal discrete-time reservoir computers with stochastic inputs and linear readouts using non-homogeneous state-affine systems

2017-12-03 · Lyudmila Grigoryeva, Juan-Pablo Ortega

A new class of non-homogeneous state-affine systems is introduced for use in reservoir computing. Sufficient conditions are identified that guarantee first, that the associated reservoir computers with linear readouts ar…

Nonlinear memory capacity of parallel time-delay reservoir computers in the processing of multidimensional signals

2015-10-13 · Lyudmila Grigoryeva, Julie Henriques, Laurent Larger, Juan-Pablo Ortega

This paper addresses the reservoir design problem in the context of delay-based reservoir computers for multidimensional input signals, parallel architectures, and real-time multitasking. First, an approximating reservoi…