Traditional Feedforward Neural Networks Research Articles

An orthogonal neural network for function approximation

This paper presents a new single-layer neural network which is based on orthogonal functions. This neural network is developed to avoid the problems of traditional feedforward neural networks such as the determination of initial weights and the numbers of layers and processing elements. The desired output accuracy determines the required number of processing elements. Because weights are unique, the training of the neural network converges rapidly. An experiment in approximating typical continuous and discrete functions is given. The results show that the neural network has excellent performance in convergence time and approximation error.

Measurement selection for parametric IC fault diagnosis

This article presents experimental results which show feedforward neural networks are well-suited for analog IC fault diagnosis. Boundary band data (BBD) measurement selection is used to reduce the computational overhead of the FFN training phase. We compare the diagnostic accuracy between traditional statistical classifiers and feedforward neural networks trained with various measurement selection criteria. The feedforward networks consistently perform as well as or better than the other classifiers in term of accuracy. Training using BBD consistently reduces the FFN training efforts without degrading the performance. Experimental results suggest that feedforward networks provide a cost efficient method for IC fault diagnosis in a large scale production testing environment.

Discrete time neural networks

Traditional feedforward neural networks are static structures that simply map input to output. To better reflect the dynamics in the biological system, time dependency is incorporated into the network by using Finite Impulse Response (FIR) linear filters to model the processes of axonal transport, synaptic modulation, and charge dissipation. While a constructive proof gives a theoretical equivalence between the class of problems solvable by the FIR model and the static structure, certain practical and computational advantages exist for the FIR model. Adaptation of the network is achieved through an efficient gradient descent algorithm, which is shown to be a temporal generalization of the popular backpropagation algorithm for static networks. Applications of the network are discussed with a detailed example of using the network for time series prediction.