A preference is not located anywhere in the agent's cognitive architecture, but it is rather a constraining of behavior which is in turn shaped by behavior. Based on this idea, a minimal model of behavioral preference is proposed. A simulated mobile agent is modeled with a plastic neurocontroller, which holds two separate high dimensional homeostatic boxes in the space of neural dynamics. An ev...

Previous work has provided the theoretical foundations of a constructive design procedure for uniform approximation of smooth functions to a chosen degree of accuracy using networks of gaus-sian radial basis functions. This construction and the guaranteed uniform bounds were then shown to provide the basis for stable adaptive neurocontrol algorithms for a class of nonlinear plants. This paper d...

We show that simple linear readouts from generic neural microcircuit models can easily be trained to generate basic arm movements. Such movement generation is independent of the arm-model used and the type of feedbacks that the circuit receives, and generalizes to new targets for reaching movements. Feedbacks that arrive with biologically realistic delays of 50-280 ms are essential for the evol...

Four-bar linkage mechanisms are of interest for many specialists in the academia and industry. However, it is one of the mechanisms that is highly nonlinear and exhibits complex behavior. Therefore, it is difficult to model and control their dynamic responses. In this paper, various control schemes are explored and tested on the four-bar mechanism to investigate the dynamical performance under ...

While traditional approaches to machine learning are sensitive to highdimensional state and action spaces, this paper demonstrates how an indirectly encoded neurocontroller for a simulated octopus arm leverages regularities and domain geometry to capture underlying motion principles and sidestep the superficial trap of dimensionality. In particular, controllers are evolved for arms with 8, 10, ...

This study investigates task -blind and task -specific training methods to determine appropriate radial basis function based neural network architectures. These neural nets identify system behavior of air-cooled chiller condensers by grouping dominant features (clustering) of measured chiller performance data. Task specific clustering proved superior but more computationally demanding than task...

This paper investigates the development o f a direct neuro-active vihration control (AVC) mechanism for vibration reduction ofa flexible plate structure. A multi layer perceptron (MLP) neuro-controller is designed to characterise the ideal controller characteristic using an online adaptation and training mechanism. The effectiveness ofthe MLP neurocontroller is then verified within the AVC syst...

In this paper, we describe our application of a neurocontroller based on Action Dependent Heuristic Dynamic Programming (ADHDP) to optimize the combustion-process for an industrial hazardous waste incineration plant. This ADHDP-controller originally was designed for online learning. That implies, that this controller starts with a randomly initialized policy and improves its performance while i...

This paper presents an adaptive neuro-controller for intelligent control of non-linear dynamical system. The formed as the fuzzy selective neural net the adaptive neuro-controller on the basе of system’s state, creates the effective control signal under random perturbations. The validity and advantages of the proposed adaptive neuro-controller are demonstrated by numerical simulations. The simu...

The field of neurocontrol, in which neural networks are used for control of complex systems, has many potential applications. One of the biggest hurdles to developing neurocontrollers is the difficulty in establishing good training data for the neural network. We propose a hybrid approach to the development of neurocontrollers that employs both evolutionary computation (EC) and neural networks ...