Reservoir Computing emerges as a solution to the difficulties faced by Recurrent Neural Networks (RNNs).
Reservoir Computing has been successfully applied in various fields including natural language processing, computational biology, neuroscience, robotics, and physics.
This survey explores the history and appeal of traditional feed-forward and recurrent neural networks, along with the theory and models of the reservoir computing paradigm.
Recent papers utilizing reservoir computing in different scientific fields are reviewed in this survey.