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.

No abstract

No abstract

The authors developed a new analysis approach for evaluation of atomic ordering in full-Heusler alloys, which is extension of the commonly used Webster model. Our model can give accurate physical formalism for the degree of atomic ordering in the L2 1 structure, including correction with respect to the fully disordered A2 structure, i.e., the model can directly evaluate the degree of L2 1 -ordering under a lower ordering structure than the complete B2-ordering structure. The proposed model was applied to full-Heusler Co 2 FeSi alloy thin films formed by rapid thermal annealing. The film formed at T A = 800 °C showed a relatively high degree of L2 1 -ordering of 83 % under a high degree of B2-ordering of 97 %.