We train recurrent neural network on a single, long, complex symbolic sequence with positive entropy. Training process is monitored through information theory based performance measures. We show that although the sequence is unpredictable, the network is able to code the sequence topological and statistical structure in recurrent neurons' activation scenarios. Such scenarios can be compactly re...

We present a novel approach to unsupervised temporal sequence processing in the form of an unsupervised, recurrent neural network based on a selforganizing map (SOM). A standard SOM clusters each input vector irrespective of context, whereas the recurrent SOM presented here clusters each input based on an input vector and a context vector. The latter acts as a recurrent conduit feeding back a 2...

an adaptive input-output linearization method for general nonlinear systems is developed without using states of the system. another key feature of this structure is the fact that, it does not need model of the system. in this scheme, neurolinearizer has few weights, so it is practical in adaptive situations.  online training of neurolinearizer is compared to model predictive recurrent training...

In this paper, an economic emission dispatch (EED) model is developed to reduce fuel cost and environmental pollution emissions. Considering the development of new energy sources in recent years, EED problem involves thermal units with valve point effect WTs. Meanwhile, it complies demand constraint generator capacity constraints. A recurrent neural network (RNN) proposed search for local optim...