Backpropagation of errors is not only hard to justify from biological perspective but also it fails to solve problems requiring complex logic. A simpler algorithm based on generation and filtering of useful random projections has better biological justification, is faster, easier to train and may in practice solve nonseparable problems of higher complexity than typical feedforward neural networ...

We propose a novel learning method for multilayered neural networks which uses feedforward supervisory signal and associates the classification of a new input with that of pre-trained input. The proposed method effectively uses rich input information in the earlier layer for robust learning and revising of the internal representation in a multilayer neural network.

In this paper neural networks have been proposed as an alternative technique to build software reliability growth models. A feedforward neural network was used to predict the number of faults initially resident in a program at the beginning of a test/debug process. To evaluate the predictive capability of the developed model data sets from various projects were used [l]. A comparison between re...

Neuro-fuzzy modeling has been intensively studied since the early nineties. Recently a method has been disclosed, that uses a classical feedforward neural network with just one hidden layer. Nodes of the hidden layer use the logistic function as activation function meanwhile the output node has a linear activation function. This paper introduces a generalization of the logistic function and eva...

We propose a new strategy for a constructive training of feedforward neural networks to classifit linearly nonseparable patterns. The algorithm results in a confguration of the first layer of the network, which is able to give a faithjtl internal representation of the input patterns. The weights of the network are obtained by the introduced CadaTron algorithm, which is able to separate clusters...

One of the well-known recurrent neural networks is the Elman network. Recently, it has been used in applications of system identification. The network has feedforward and feedback connections. It can be trained essentially as a feedforward network by means of the basic backpropagation algorithm, but its feedback connections have to be kept constant. For training success, it is important to sele...

This paper develops the theory for tracking control using the nonlinear H1 control design methodology for a class of nonlinear input affine systems. The authors use a two-step process of first designing the feedforward part of the controller to design for perfect trajectory following and then design the feedback part of the controller using nonlinear H1 regulator theory. Results for infinite-ti...

This paper focuses on the potential of the learning aspects of assessment. The term ‘learning-oriented assessment’ is introduced and three elements of it are elaborated: assessment tasks as learning tasks; student involvement in assessment as peeror self-evaluators; and feedback as feedforward. I also indicate how learningoriented assessment was promoted at the institutional level through a ref...

This paper incorporates robustness into neural network modeling and proposes a novel two-phase robustness analysis approach for determining the optimal feedforward neural network (FNN) architecture in terms of Hellinger distance of probability density function (PDF) of error distribution. The proposed approach is illustrated with an example in this paper.