A method is presented for immunizing an Echo State Network against slow, task-irrelevant variation in its input. The main idea is to extract some principal components of the smoothed reservoir dynamics, and augment the reservoir with a feedback controller which attempts to pull these components to zero. This leads to a “homeostatic” self-stabilization of the reservoir dynamics. A proof-of-princ...

Reservoir computing provides a simpler paradigm of training recurrent networks by initialising and adapting the recurrent connections separately to a supervised linear readout. This creates a problem, though. As the recurrent weights and topology are now separated from adapting to the task, there is a burden on the reservoir designer to construct an effective network that happens to produce sta...

The Aras reservoir, located in the north-west of Iran, plays an important role in fisheries, drinking and agricultural water supplies and recreational activities in the region. This study was performed to characterize the seasonal fluctuations of phytoplankton communities and their relationship with environmental factors in the Aras reservoir from August 2013 to May 2014. Sampling was carried o...

This paper presents a Multi-objective Evolutionary Algorithm (MOEA) to derive a set of optimal operation policies for a multipurpose reservoir system. One of the main goals in multiobjective optimization is to find a set of well distributed optimal solutions along the Pareto front. Classical optimization methods often fail in attaining a good Pareto front. To overcome the drawbacks faced by the...