When training a feedforward stochastic gradient descendent trained neural network, there is possibility of not learning batch patterns correctly that causes the network to fail in predictions areas adjacent those patterns. This problem has usually been resolved by directly adding more complexity normally increasing number layers, which means it will be heavier run on workstation. In this paper,...

Feedforward neural networks trained by error backpropagation are examples of nonparametric regression estimators. We present a tutorial on nonparametric inference and its relation to neural networks, and we use the statistical viewpoint to highlight strengths and weaknesses of neural models. We illustrate the main points with some recognition experiments involving artificial data as well as han...

Feedforward neural networks provide the dominant model of how the brain performs visual object recognition. However, these networks lack the lateral and feedback connections, and the resulting recurrent neuronal dynamics, of the ventral visual pathway in the human and non-human primate brain. Here we investigate recurrent convolutional neural networks with bottom-up (B), lateral (L), and top-do...

This paper proposes an evolutionary design methodology of multilayer feedforward neural networks based on constructive approach. We elaborate an adjustable processing element as primitive neuron model. The neural layer can be constructed by assembling several neurons. The multilayer neural network can be finally constructed through cascading several neural layers. The constructive approach faci...

This paper investigates the identification of nonlinear systems by utilizing soft-computing approaches. As the identification methods, Feedforward Neural Network architecture (FNN), Radial Basis Function Neural Networks (RBFNN), Runge-Kutta Neural Networks (RKNN) and Adaptive Neuro Fuzzy Inference Systems (ANFIS) based identification mechanisms are studied and their performances are comparative...

This paper introduces quantum neural networks (QNNs), a class of feedforward neural networks (FFNNs) inherently capable of estimating the structure of a feature space in the form of fuzzy sets. The hidden units of these networks develop quantized representations of the sample information provided by the training data set in various graded levels of certainty. Unlike other approaches attempting ...

In our previous work we proposed some extensions of the Levenberg-Marquardt algorithm; the Bacterial Memetic Algorithm and the Bacterial Memetic Algorithm with Modified Operator Execution Order for fuzzy rule base extraction from inputoutput data. Furthermore, we have investigated fuzzy flip-flop based feedforward neural networks. In this paper we introduce the adaptation of the Bacterial Memet...