Neural networks (NNs) have been successfully applied to solve a variety of application problems including classification and function approximation. They are especially useful as function approximators because they do not require prior knowledge of the input data distribution and they have been shown to be universal approximators. In many applications, it is desirable to extract knowledge that ...

A Sensor Failure Detection, Identification and Accommodation (SFDIA) scheme for a flight control system with dual physical redundancy is proposed, with the focus on taking advantage of analytical redundancy for sensor failure purposes. The proposed scheme, based on a set of neural on-line approximators, has shown to be able to provide desirable SFDIA capabilities. The designed approximators are...

The design of multivariable control systems requires identification of the effects of individual inputs on each of the outputs. In many complex systems whose behavior is described by a large set of partial differential equations, the solution cannot be implemented in real time. This paper presents an overview of several linear and nonlinear approximators – least squares, principle component reg...

We interpret a type of fuzzy controller as an inter polator of B spline hypersurfaces B spline basis func tions of di erent orders are regarded as a class of mem bership functions MFs with some special properties These properties lead to several interesting conclusions about fuzzy controllers if such membership functions are employed to specify the linguistic terms of the input variables We sho...

On large problems, reinforcement learning systems must use parame-terized function approximators such as neural networks in order to generalize between similar situations and actions. In these cases there are no strong theoretical results on the accuracy of convergence, and computational results have been mixed. In particular, Boyan and Moore reported at last year's meeting a series of negative...

In many real-world applications, predictive methods are used to provide inputs for downstream optimization problems. It has been shown that using the task-based objective learn intermediate model is often better than only task objectives, such as prediction error. The learning in former approach referred end-to-end learning. difficulty lies differentiating through problem. Therefore, we propose...

It is well known that conservative mechanical systems exhibit local oscillatory behaviours due to their elastic and gravitational potentials, which completely characterise these periodic motions together with the inertial properties of system. The classification geometric characterisation are in an on-going secular debate, recently led so-called eigenmanifold theory. characterises nonlinear osc...

Different predictors and their approximators in nonlinear prediction regression models are studied. The minimal value of the mean squared error (MSE) is derived. Some approximate formulae for the MSE of ordinary and weighted least squares predictors are given.

The application of reinforcement learning to problems with continuous domains requires representing the value function by means of function approximation. We identify two aspects of reinforcement learning that make the function approximation process hard: non-stationarity of the target function and biased sampling. Non-stationarity is the result of the bootstrapping nature of dynamic programmin...

Temporal difference methods are theoretically grounded and empirically effective methods for addressing reinforcement learning problems. In most real-world reinforcement learning tasks, TD methods require a function approximator to represent the value function. However, using function approximators requires manually making crucial representational decisions. This paper investigates evolutionary...