By Topic

# Neural Networks for Signal Processing VII. Proceedings of the 1997 IEEE Signal Processing Society Workshop

## Filter Results

Displaying Results 1 - 25 of 74
• ### Neural Networks for Signal Processing VII. Proceedings of the 1997 IEEE Signal Processing Society Workshop

Publication Year: 1997
| PDF (311 KB)
• ### A neural network equalizer with the fuzzy decision learning rule

Publication Year: 1997, Page(s):551 - 559
| | PDF (377 KB)

We propose a neural network equalizer with a fuzzy decision learning rule based on the generalized probabilistic descent algorithm with the minimum decision error formulation. The neural network used is the multi-layer perceptron. It is shown that the decision region overlapped by noise can be overcome by the use of a fuzzy decision learning rule based on the generalized probabilistic descent algo... View full abstract»

• ### Author index

Publication Year: 1997, Page(s):665 - 667
| PDF (85 KB)
• ### Uniform approximation and the complexity of neural networks

Publication Year: 1997, Page(s):141 - 148
Cited by:  Papers (1)
| | PDF (320 KB)

Studies some of the approximating properties of feedforward neural networks as a function of the number of nodes. Two cases are considered: sigmoidal and radial basis function networks. Bounds for the approximation error are given. The methods through which we arrive at the bounds are constructive. The error studied is the L or sup error View full abstract»

• ### An improved training algorithm for support vector machines

Publication Year: 1997, Page(s):276 - 285
Cited by:  Papers (250)  |  Patents (17)
| | PDF (432 KB)

We investigate the problem of training a support vector machine (SVM) on a very large database in the case in which the number of support vectors is also very large. Training a SVM is equivalent to solving a linearly constrained quadratic programming (QP) problem in a number of variables equal to the number of data points. This optimization problem is known to be challenging when the number of dat... View full abstract»

• ### A multiple-classifier architecture for ECG beat classification

Publication Year: 1997, Page(s):172 - 181
Cited by:  Papers (2)  |  Patents (1)
| | PDF (516 KB)

We investigate the use of the modular architecture of multiple clustering based pattern classifiers for ECG beat classification using the MIT/BIH arrhythmia database. The feature space is divided into several regions and individual classifiers are developed for each region separately. Then the outputs of these classifiers are combined using two competing combination rules: a winner decides all met... View full abstract»

• ### Induced specialization of context units for temporal pattern recognition and reproduction

Publication Year: 1997, Page(s):131 - 140
| | PDF (464 KB)

Additional inputs to a feedforward network, derived from the output of the hidden layer neurons, allow a feedforward network to deal with temporal pattern recognition and reproduction tasks. These network derived' or context' inputs augment the `true' inputs to the network and allow the network to retain past information necessary for temporal sequence processing. The choice of which hidden neur... View full abstract»

• ### A DCT-based adaptive metric learning model using asymptotic local information measure

Publication Year: 1997, Page(s):521 - 530
Cited by:  Papers (2)
| | PDF (416 KB)

We present an adaptive metric learning vector quantization procedure based on the discrete-cosine transform (DCT) for accurate face recognition used in multimedia applications. Since the set of learning samples may be small, we employ a mixture model of prior distributions. The model selection method, which minimizes the cross entropy between the real distribution and the modeled one, is presented... View full abstract»

• ### One-unit contrast functions for independent component analysis: a statistical analysis

Publication Year: 1997, Page(s):388 - 397
Cited by:  Papers (36)
| | PDF (544 KB)

The author (1997) introduced a large family of one-unit contrast functions to be used in independent component analysis (ICA). In this paper, the family is analyzed mathematically in the case of a finite sample. Two aspects of the estimators obtained using such contrast functions are considered: asymptotic variance, and robustness against outliers. An expression for the contrast function that mini... View full abstract»

• ### A deterministic annealing approach to discriminative hidden Markov model design

Publication Year: 1997, Page(s):266 - 275
Cited by:  Papers (3)
| | PDF (524 KB)

We present the problem of designing a classifier system based on hidden Markov models (HMMs) from a labeled training set with the objective of minimizing the rate of misclassification. To design the globally optimal recognizer, all the HMMs must be jointly optimized to minimize the number of mis-classified training patterns. This is a difficult design problem which we attack using the technique of... View full abstract»

• ### Dynamics modelling in brain circulation

Publication Year: 1997, Page(s):162 - 171
Cited by:  Patents (3)
| | PDF (500 KB)

Two different measurement modalities, one related to blood flow, the other related to brain metabolism are monitored in a head injury patient and analyzed by using the method of surrogate data. That is applied against a hierarchy of two-dimensional Markov processes, designed to model a possible deterministic behaviour of the system and correlations between the two observed variables. Two-layered f... View full abstract»

• ### Wave propagation as a neural coupling mechanism: hardware for self-organizing feature maps and the representation of temporal sequences

Publication Year: 1997, Page(s):306 - 315
| | PDF (532 KB)

Wave propagation within a “cortex” of neurons is introduced as a neural coupling mechanism. Using this effect for the control of the neural learning process, the network generates self-organizing feature maps. Additionally, wave propagation is used to influence the neural competition in representing the input of the network. By this means the network is able to represent temporal aspec... View full abstract»

• ### Blind source separation and deconvolution by dynamic component analysis

Publication Year: 1997, Page(s):456 - 465
Cited by:  Papers (5)
| | PDF (444 KB)

We derive new unsupervised learning rules for blind separation of mixed and convolved sources. These rules are nonlinear in the signals and thus exploit high-order spatiotemporal statistics to achieve separation. The derivation is based on a global optimization formulation of the separation problem, yielding a stable algorithm. Different rules are obtained from frequency- and time-domain optimizat... View full abstract»

• ### Multiple and time-varying dynamic modelling capabilities of recurrent neural networks

Publication Year: 1997, Page(s):121 - 130
Cited by:  Papers (3)
| | PDF (484 KB)

We propose some theories regarding the dynamical system representational capabilities of recurrent neural networks with real-valued inputs and outputs. It is shown that multiple nonlinear dynamic systems can be approximated within a single nonlinear model structure. A relationship is identified between this class of recurrent network, hybrid models and agent based systems View full abstract»

• ### Nonlinear prediction of chaotic time series using support vector machines

Publication Year: 1997, Page(s):511 - 520
Cited by:  Papers (137)
| | PDF (468 KB)

A novel method for regression has been recently proposed by Vapnik et al. (1995, 1996). The technique, called support vector machine (SVM), is very well founded from the mathematical point of view and seems to provide a new insight in function approximation. We implemented the SVM and tested it on a database of chaotic time series previously used to compare the performances of different approximat... View full abstract»

• ### Blind separation of noisy mixtures

Publication Year: 1997, Page(s): 387
Cited by:  Papers (1)
| | PDF (36 KB)

First Page of the Article
View full abstract»

• ### The gamma MLP-using multiple temporal resolutions for improved classification

Publication Year: 1997, Page(s):256 - 265
Cited by:  Papers (2)
| | PDF (508 KB)

We (1996) have previously introduced the gamma multilayer perceptron (MLP) which is defined as an MLP with the usual synaptic weights replaced by gamma filters and associated gain terms throughout all layers. In this paper we apply the gamma MLP to a larger scale speech phoneme recognition problem, analyze the operation of the network, and investigate why the gamma MLP can perform better than alte... View full abstract»

• ### Blind signal deconvolution by spatio-temporal decorrelation and demixing

Publication Year: 1997, Page(s):426 - 435
Cited by:  Papers (7)
| | PDF (468 KB)

We present a simple efficient local unsupervised learning algorithm for online adaptive multichannel blind deconvolution and separation of i.i.d. sources. Under mild conditions, there exits a stable inverse system so that the source signals can be exactly recovered from their convolutive mixtures. Based on the existence of the inverse filter, we construct a two-stage neural network which consists ... View full abstract»

• ### Multi-linguistic handwritten character recognition by Bayesian decision-based neural networks

Publication Year: 1997, Page(s):626 - 635
| | PDF (528 KB)

This paper proposes a multi-linguistic handwritten characters recognition system based on Bayesian decision-based neural networks (BDNN). The proposed system consists of two modules: first, a coarse classifier determines an input character to one of the pre-defined subclasses partitioned from a large character set, such as Chinese mixed with alphanumerics. Then a character recognizer determines th... View full abstract»

• ### Mixture of discriminative learning experts of constant sensitivity for automated cytology screening

Publication Year: 1997, Page(s):152 - 161
Cited by:  Papers (3)
| | PDF (504 KB)

One practical objective in an automated cytology screening task is to obtain as high as possible specificity (the percentage of normal slides being classified as normal) while attaining acceptable (predefined) constant sensitivity. In this paper, we propose a new learning algorithm which continuously improves the specificity while maintaining constant sensitivity for pattern classification problem... View full abstract»

• ### Combination of adaptive signal processing and neural classification using an extended backpropagation algorithm

Publication Year: 1997, Page(s):296 - 305
| | PDF (412 KB)

Beside the use of purely neural systems, the combination of preprocessing units and neural classifiers has been used for a variety of signal segmentation and classification tasks. Whereas this approach reduces the input dimensionality as well as the complexity of the classification problem, its performance crucially depends on a proper preprocessing scheme, i.e., feature extraction. In this contri... View full abstract»

• ### MR brain image classification by multimodal perceptron tree neural network

Publication Year: 1997, Page(s):189 - 198
Cited by:  Patents (1)
| | PDF (564 KB)

We propose a multimodal perceptron tree (MMPT) neural network to segment magnetic resonance (MR) images. The architecture consists of simple networks-neurons, hierarchically connected in a tree structure. The latter is built up during training by the adopted depth-first searching technique augmented with choosing the best hyperplane split of the feature subspace at each tree node. This neural netw... View full abstract»

• ### A chaotic annealing neural network and its application to direction estimation of spatial signal sources

Publication Year: 1997, Page(s):541 - 550
Cited by:  Papers (2)
| | PDF (480 KB)

A chaotic annealing neural network model based on transient chaos and dynamic gain is proposed for solving optimization problems with continuous-variables, such as the maximal likelihood estimation of spatial signal sources considered in this article. Compared to conventional neural networks only with point attractors, the proposed neural network has richer and more flexible dynamics, which are ex... View full abstract»

• ### Segmentation and identification of drifting dynamical systems

Publication Year: 1997, Page(s):326 - 335
Cited by:  Papers (7)  |  Patents (1)
| | PDF (544 KB)

A method for the analysis of nonstationary time series with multiple operating modes is presented. In particular, it is possible to detect and to model a switching of the dynamics and also a less abrupt, time consuming drift from one mode to another. This is achieved by an unsupervised algorithm that segments the data according to inherent modes, and a subsequent search through the space of possib... View full abstract»

• ### Recurrent canonical piecewise linear network: theory and application

Publication Year: 1997, Page(s):446 - 455
| | PDF (492 KB)

A recurrent canonical piecewise linear (RCPL) network is defined by combining the canonical piecewise linear function with the autoregressive moving average (ARMA) model such that an augmented input space is partitioned into regions where an ARMA model is used in each. Properties of the RCPL network are discussed. Particularly, it is shown that the RCPL function is a contractive mapping and is sta... View full abstract»