By Topic

Neural Networks, IEEE Transactions on

Issue 6 • Date Nov. 1999

Filter Results

Displaying Results 1 - 25 of 32
  • Corrections to "a new error function at hidden layers for fast training of multilayer perceptrons"

    Publication Year: 1999 , Page(s): 1541
    Cited by:  Papers (1)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (84 KB)  

    First Page of the Article
    View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Author index

    Publication Year: 1999 , Page(s): 1 - 6
    Request Permissions | PDF file iconPDF (216 KB)  
    Freely Available from IEEE
  • Subject index

    Publication Year: 1999 , Page(s): 6 - 20
    Request Permissions | PDF file iconPDF (231 KB)  
    Freely Available from IEEE
  • Design quality and robustness with neural networks

    Publication Year: 1999 , Page(s): 1518 - 1527
    Cited by:  Papers (7)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (180 KB)  

    Data sets that are gathered for industrial applications are frequently noisy and present challenges that necessitate use of different methodologies. We present a successful example of generating concise and accurate neural-network models for multiple quality characteristics in injection molding. These models map process measurements to product quality. They are used for product and process design,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sample selection via clustering to construct support vector-like classifiers

    Publication Year: 1999 , Page(s): 1474 - 1481
    Cited by:  Papers (25)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (136 KB)  

    Explores the possibility of constructing RBF classifiers which, somewhat like support vector machines, use a reduced number of samples as centroids, by means of selecting samples in a direct way. Because sample selection is viewed as a hard computational problem, this selection is done after a previous vector quantization: this way obtains also other similar machines using centroids selected from ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimate of exponential convergence rate and exponential stability for neural networks

    Publication Year: 1999 , Page(s): 1487 - 1493
    Cited by:  Papers (60)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (204 KB)  

    Estimates of exponential convergence rate and exponential stability are studied for a class of neural networks which includes Hopfield neural networks and cellular neural networks. Both local and global exponential convergence are discussed. Theorems for estimation of the exponential convergence rate are established and the bounds on the rate of convergence are given. The domains of attraction in ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A dynamic channel assignment policy through Q-learning

    Publication Year: 1999 , Page(s): 1443 - 1455
    Cited by:  Papers (25)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (280 KB)  

    One of the fundamental issues in the operation of a mobile communication system is the assignment of channels to cells and to calls. This paper presents a novel approach to solving the dynamic channel assignment (DCA) problem by using a form of real-time reinforcement learning known as Q-learning in conjunction with neural network representation. Instead of relying on a known teacher the system is... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An adaptable time-delay neural-network algorithm for image sequence analysis

    Publication Year: 1999 , Page(s): 1531 - 1536
    Cited by:  Papers (48)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (564 KB)  

    We present an algorithm based on a time-delay neural network with spatio-temporal receptive fields and adaptable time delays for image sequence analysis. Our main result is that tedious manual adaptation of the temporal size of the receptive fields can be avoided by employing a method to adapt the corresponding time delay and related network structure parameters during the training process View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiple neural-network-based adaptive controller using orthonormal activation function neural networks

    Publication Year: 1999 , Page(s): 1494 - 1501
    Cited by:  Papers (7)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (212 KB)  

    A direct adaptive control scheme is developed using orthonormal activation function-based neural networks (OAFNNs) for trajectory tracking control of a class of nonlinear systems. Multiple OAFNNs are employed in these controllers for feedforward compensation of unknown system dynamics. Choice of multiple OAFNNs allows a reduction in overall network size reducing the computational requirements. The... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stable dynamic backpropagation learning in recurrent neural networks

    Publication Year: 1999 , Page(s): 1321 - 1334
    Cited by:  Papers (53)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (604 KB)  

    To avoid unstable phenomenon during the learning process, two new learning schemes, called the multiplier and constrained learning rate algorithms, are proposed in this paper to provide stable adaptive updating processes for both the synaptic and somatic parameters of the network. Based on the explicit stability conditions, in the multiplier method these conditions are introduced into the iterativ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Toward an optimal PRNN-based nonlinear predictor

    Publication Year: 1999 , Page(s): 1435 - 1442
    Cited by:  Papers (18)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (176 KB)  

    We present an approach for selecting optimal parameters for the pipelined recurrent neural network (PRNN) in the paradigm of nonlinear and nonstationary signal prediction. We consider the role of nesting, which is inherent to the PRNN architecture. The corresponding number of nested modules needed for a certain prediction task, and their contribution toward the final prediction gain give a thoroug... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Exploring constructive cascade networks

    Publication Year: 1999 , Page(s): 1335 - 1350
    Cited by:  Papers (25)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (416 KB)  

    Constructive algorithms have proved to be powerful methods for training feedforward neural networks. An important property of these algorithms is generalization. A series of empirical studies were performed to examine the effect of regularization on generalization in constructive cascade algorithms. It was found that the combination of early stopping and regularization resulted in better generaliz... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Nonlinear adaptive trajectory tracking using dynamic neural networks

    Publication Year: 1999 , Page(s): 1402 - 1411
    Cited by:  Papers (76)  |  Patents (1)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (292 KB)  

    In this paper the adaptive nonlinear identification and trajectory tracking are discussed via dynamic neural networks. By means of a Lyapunov-like analysis we determine stability conditions for the identification error. Then we analyze the trajectory tracking error by a local optimal controller. An algebraic Riccati equation and a differential one are used for the identification and the tracking e... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • ANN-DT: an algorithm for extraction of decision trees from artificial neural networks

    Publication Year: 1999 , Page(s): 1392 - 1401
    Cited by:  Papers (28)  |  Patents (1)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (176 KB)  

    Although artificial neural networks can represent a variety of complex systems with a high degree of accuracy, these connectionist models are difficult to interpret. This significantly limits the applicability of neural networks in practice, especially where a premium is placed on the comprehensibility or reliability of systems. A novel artificial neural-network decision tree algorithm (ANN-DT) is... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Partition-based and sharp uniform error bounds

    Publication Year: 1999 , Page(s): 1315 - 1320
    Cited by:  Papers (2)  |  Patents (1)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (128 KB)  

    This paper develops probabilistic bounds on out-of-sample error rates for several classifiers using a single set of in-sample data. The bounds are based on probabilities over partitions of the union of in-sample and out-of-sample data into in-sample and out-of-sample data sets, The bounds apply when in-sample and out-of-sample data are drawn from the same distribution. Partition-based bounds are s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Complex cell prototype representation for face recognition

    Publication Year: 1999 , Page(s): 1528 - 1531
    Cited by:  Papers (1)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (204 KB)  

    We propose a face recognition system based on a biologically inspired filtering method. Our work differs from previous proposals in: 1) the multistage filtering method employed; 2) the pyramid structure used, and most importantly; 3) the prototype construction scheme to determine the models stored in memory. The method is much simpler than previous proposals and relatively inexpensive computationa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stability analysis of Hopfield-type neural networks

    Publication Year: 1999 , Page(s): 1366 - 1374
    Cited by:  Papers (21)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (208 KB)  

    The paper applies several concepts in robust control research such as linear matrix inequalities, edge theorem, parameter-dependent Lyapunov function, and Popov criteria to investigate the stability property of Hopfield-type neural networks. The existence and uniqueness of an equilibrium is formulated as a matrix determinant problem. An induction scheme is used to find the equilibrium. To verify w... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The DSFPN, a new neural network for optical character recognition

    Publication Year: 1999 , Page(s): 1465 - 1473
    Cited by:  Papers (2)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (200 KB)  

    A new type of neural network for recognition tasks is presented. The network, called the dynamic supervised forward-propagation network (DSFPN), is based on the forward only version of the counterpropagation network (CPN). The DSFPN, trains using a supervised algorithm and can grow dynamically during training, allowing subclasses in the training data to be learnt in an unsupervised manner. It is s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bayesian approach to neural-network modeling with input uncertainty

    Publication Year: 1999 , Page(s): 1261 - 1270
    Cited by:  Papers (17)  |  Patents (9)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (208 KB)  

    It is generally assumed when using Bayesian inference methods for neural networks that the input data contains no noise or corruption. For real-world (errors in variable) problems this is clearly an unsafe assumption. This paper presents a Bayesian neural-network framework which allows for input noise provided that some model of the noise process exists. In the limit where the noise process is sma... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The application of neural networks to the papermaking industry

    Publication Year: 1999 , Page(s): 1456 - 1464
    Cited by:  Papers (18)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (128 KB)  

    This paper describes the application of neural network techniques to the papermaking industry, particularly for the prediction of paper “curl”. Paper curl is an important quality measure that can only be measured reliably off-line after manufacture, making it difficult to control. Here, we predict, before paper manufacture from characteristics of the current reel, whether the paper cur... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Shape recovery from shading by a new neural-based reflectance model

    Publication Year: 1999 , Page(s): 1536 - 1541
    Cited by:  Papers (11)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (332 KB)  

    We present a neural-based reflectance model of which the physical parameters of the reflectivity under different lighting conditions are interpreted by the network weights. The idea of our method is to optimize a proper reflectance model by an effective learning algorithm and to recover the object surface by a simple shape from shading recursive algorithm with this resulting model. Experiments, in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Inverting feedforward neural networks using linear and nonlinear programming

    Publication Year: 1999 , Page(s): 1271 - 1290
    Cited by:  Papers (6)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (524 KB)  

    The problem of inverting trained feedforward neural networks is to find the inputs which yield a given output. In general, this problem is an ill-posed problem. We present a method for dealing with the inverse problem by using mathematical programming techniques. The principal idea behind the method is to formulate the inverse problem as a nonlinear programming problem, a separable programming (SP... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • RBF principal manifolds for process monitoring

    Publication Year: 1999 , Page(s): 1424 - 1434
    Cited by:  Papers (24)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (204 KB)  

    This paper describes a novel means for creating a nonlinear extension of principal component analysis (PCA) using radial basis function (RBF) networks. This algorithm comprises two distinct stages: projection and self-consistency. The projection stage contains a single network, trained to project data from a high- to a low-dimensional space. Training requires solution of a generalized eigenvector ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Relative loss bounds for single neurons

    Publication Year: 1999 , Page(s): 1291 - 1304
    Cited by:  Papers (9)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (348 KB)  

    We analyze and compare the well-known gradient descent algorithm and the more recent exponentiated gradient algorithm for training a single neuron with an arbitrary transfer function. Both algorithms are easily generalized to larger neural networks, and the generalization of gradient descent is the standard backpropagation algorithm. We prove worst-case loss bounds for both algorithms in the singl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neural-network method for the nonlinear servomechanism problem

    Publication Year: 1999 , Page(s): 1412 - 1423
    Cited by:  Papers (15)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (292 KB)  

    The solution of the nonlinear servomechanism problem relies on the solvability of a set of mixed nonlinear partial differential and algebraic equations known as the regulator equations. Due to the nonlinear nature, it is difficult to obtain the exact solution of the regulator equations. This paper proposes to solve the regulator equations based on a class of recurrent neural network, which has the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.

Aims & Scope

IEEE Transactions on Neural Networks is devoted to the science and technology of neural networks, which disclose significant technical knowledge, exploratory developments, and applications of neural networks from biology to software to hardware.

 

This Transactions ceased production in 2011. The current retitled publication is IEEE Transactions on Neural Networks and Learning Systems.

Full Aims & Scope