Using mutual information for selecting features in supervised neural net learning
This paper investigates the application of the mutual information criterion to evaluate a set of candidate features and to select an informative subset to be used as input data for a neural network classifier. Because the mutual information measures ...
Second-order bounds on the domain of attraction and the rate of convergence of nonlinear dynamical systems and neural networks
We present a method for analyzing the convergence properties of nonlinear dynamical systems yielding second-order bounds on the domain of attraction of an asymptotically stable equilibrium point and on the time of convergence in the estimated domain. We ...
Self-creating and organizing neural networks
We have developed a self-creating and organizing unsupervised learning algorithm for artificial neural networks. In this study, we introduce SCONN and SCONN2 as two versions of self-creating and organizing neural network (SCONN) algorithms. SCONN ...
Adaptation of the relaxation method for learning in bidirectional associative memory
An iterative learning algorithm called PRLAB is described for the discrete bidirectional associative memory (BAM). Guaranteed recall of all training pairs is ensured by PRLAB. The proposed algorithm is significant in many ways. Unlike many existing ...
Learning in linear systolic neural network engines: analysis and implementation
Linear systolic processor arrays are a widely proposed digital architecture for neural networks. This paper reports the analysis of a range of training algorithms implemented on a linear systolic ring, with a view to (a) identifying low-level ...
Radial basis function neural network for approximation and estimation of nonlinear stochastic dynamic systems
This paper presents a means to approximate the dynamic and static equations of stochastic nonlinear systems and to estimate state variables based on radial basis function neural network (RBFNN). After a nonparametric approximate model of the system is ...
A neural network model of causality
This paper proposes a model for commonsense causal reasoning, based on the basic idea of neural networks. After an analysis of the advantages and limitations of existing accounts of causality, a fuzzy logic based formalism FEL is proposed that takes ...
How delays affect neural dynamics and learning
We investigate the effects of delays on the dynamics and, in particular, on the oscillatory properties of simple neural network models. We extend previously known results regarding the effects of delays on stability and convergence properties. We treat ...
Diffusion network architectures for implementation of Gibbs samplers with applications to assignment problems
In this paper, analog circuit designs for implementations of Gibbs samplers are presented, which offer fully parallel computation. The Gibbs sampler for a discrete solution space (or Boltzmann machine) can be used to solve both deterministic and ...
Neural network control of communications systems
Neural networks appear well suited to applications in the control of communications systems for two reasons: adaptivity and high speed. This paper describes application of neural networks to two problems, admission control and switch control, which ...
Weight shifting techniques for self-recovery neural networks
In this paper, a self-recovery technique of feedforward neural networks called weight shifting and its analytical models are proposed. The technique is applied to recover a network when some faulty links and/or neurons occur during the operation. If ...
Acoustic-to-phonetic mapping using recurrent neural networks
This paper describes the application of artificial neural networks to acoustic-to-phonetic mapping. The experiments described are typical of problems in speech recognition in which the temporal nature of the input sequence is critical. The specific task ...
Novel heterostructure device for electronic pulse-mode neural circuits
A new approach to the hardware implementation of artificial, electronic pulse-mode neural circuits is proposed and demonstrated based on the use of a novel heterostructure device that exhibits an S-type current-voltage characteristic. The new device ...
Fuzzy logic and neural networks: clips from the field
This is a review of a video consisting of clips from presentations made at the Second IEEE International Conference on Fuzzy Systems (1993) and the 1993 IEEE International Conference on Neural Networks. Each video clip describes significant achievements ...
Information processing with fuzzy logic-Piero Bonissone
This is a review of a video on the foundations of approximate reasoning systems. The outline found in the visual materials accompanying the video refers to the lecture as fuzzy information systems (approximate reasoning systems). Almost half of the tape ...