[4][5] In these early models[4][5] the memory in the network took the form of both short-term synaptic plasticity and activity mediated by recurrent connections.
In other early reservoir neural network models the memory of the recent stimulus history was provided solely by the recurrent activity.
[3][6][7] Overall, the general concept of reservoir computing stems from the use of recursive connections within neural networks to create a complex dynamical system.
[9] The resultant complexity of such recurrent neural networks was found to be useful in solving a variety of problems including language processing and dynamic system modeling.
In recent years semiconductor lasers have attracted considerable interest as computation can be fast and energy efficient compared to electrical components.
[10][11] In 2018, a physical realization of a quantum reservoir computing architecture was demonstrated in the form of nuclear spins within a molecular solid.
[11] However, the nuclear spin experiments in [11] did not demonstrate quantum reservoir computing per se as they did not involve processing of sequential data.
Rather the data were vector inputs, which makes this more accurately a demonstration of quantum implementation of a random kitchen sink[12] algorithm (also going by the name of extreme learning machines in some communities).
Reservoirs are able to store information by connecting the units in recurrent loops, where the previous input affects the next response.
[18][8] Virtual reservoirs can be designed to have non-linearity and recurrent loops, but, unlike neural networks, the connections between units are randomized and remain unchanged throughout computation.
[19] In this architecture, an input layer feeds into a high dimensional dynamical system which is read out by a trainable single-layer perceptron.
[29] In principle, such reservoir computers could be implemented with controlled multimode optical parametric processes,[34] however efficient extraction of the output from the system is challenging especially in the quantum regime where measurement back-action must be taken into account.
[10] In this architecture, quantum mechanical coupling between spins of neighboring atoms within the molecular solid provides the non-linearity required to create the higher-dimensional computational space.