An introduction to reservoir computing
This is an incremental introduction to reservoir computing for researchers interested in implementing neural networks in physical systems.
The chapter introduces reservoir computing as a method to address the challenge of training artificial neural networks in physical systems by using high-dimensional recurrent networks and training only the final layer, and it presents various physical implementations across electronics, photonics, spintronics, mechanics, biology, and quantum computing.
There is a growing interest in the development of artificial neural networks that are implemented in a physical system. A major challenge in this context is that these networks are difficult to train since training here would require a change of physical parameters rather than simply of coefficients in a computer program. For this reason, reservoir computing, where one employs high-dimensional recurrent networks and trains only the final layer, is widely used in this context. In this chapter, I introduce the basic concepts of reservoir computing. Moreover, I present some important physical implementations coming from electronics, photonics, spintronics, mechanics, and biology. Finally, I provide a brief discussion of quantum reservoir computing.