Time Shifts to Reduce the Size of Reservoir Computers
This reduces the complexity and improves the speed of reservoir computers, particularly for analog implementations, though it appears incremental as it builds on existing reservoir computing methods.
The paper tackles the problem of reservoir computers requiring hundreds to thousands of nodes for accurate results, which complicates analysis and analog implementation, by introducing a time-shifting technique that divides the system into a small set of nonlinear nodes and time-shifted output signals, achieving excellent performance with only a small number of virtual nodes.
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 connections. In order to achieve accurate results, the reservoir usually contains hundreds to thousands of nodes. This high dimensionality makes it difficult to analyze the reservoir computer using tools from dynamical systems theory. Additionally, the need to create and connect large numbers of nonlinear nodes makes it difficult to design and build analog reservoir computers that can be faster and consume less power than digital reservoir computers. We demonstrate here that a reservoir computer may be divided into two parts; a small set of nonlinear nodes (the reservoir), and a separate set of time-shifted reservoir output signals. The time-shifted output signals serve to increase the rank and memory of the reservoir computer, and the set of nonlinear nodes may create an embedding of the input dynamical system. We use this time-shifting technique to obtain excellent performance from an opto-electronic delay-based reservoir computer with only a small number of virtual nodes. Because only a few nonlinear nodes are required, construction of a reservoir computer becomes much easier, and delay-based reservoir computers can operate at much higher speeds.