"Reservoir computing (RC) is a new framework for neural computation.
A reservoir is usually a recurrent neural network with fixed random connections.
In this article, we propose an RC model in which the connections in the reservoir are modifiable.
We apply our RC model to trace eyeblink conditioning.
The reservoir bridged the gap of an interstimulus interval between the conditioned and unconditioned stimuli, and a readout neuron was able to learn and express the timed conditioned response."
Yamazaki T, Tanaka S (2009) Robust Reservoir Generation by Correlation-Based Learning Advances in Artificial Neural Systems 2009:1-7