Several ways to solve the MSO problem

The so called MSO-problem, – a simple superposition of two or more sinusoidal waves –, has recently been discussed as a benchmark problem for reservoir computing and was shown to be not learnable by standard echo state regression. However, we show that are at least three simple ways to learn the MSO signal by introducing a time window on the input, by changing the network time step to match the sampling rate of the signal, and by reservoir adaptation. The latter approach is based on an universal principle to implement a sparsity constraint on the network activity patterns which improves spatio-temporal encoding in the network.

• Type: Conference
• Year: 2007
• Where: ESANN
• Authors: Jochen J. Steil
• Keywords: Echo State Regression, ESANN 2007, Network Time Step, Neural Networks, Simple Superposition