By Topic

Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium

2000

Go

Filter Results

Displaying Results 1 - 25 of 107
  • A reconfigurable neural environment on active networks

    Publication Year: 2000, Page(s):105 - 108 vol.6
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (312 KB)

    This paper proposes the deployment of a neural network computing environment on Active Networks. Active Networks are packet-switched computer networks in which packets can contain code fragments that are executed on the intermediate nodes. This feature allows the injection of small pieces of codes to deal with computer network problems directly into the network core, and the adoption of new comput... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks - IJCNN 2000 [front matter]

    Publication Year: 2000, Page(s):i - xxxii
    Request permission for commercial reuse | PDF file iconPDF (4871 KB)
    Freely Available from IEEE
  • Representative evolution: a simple and efficient algorithm for artificial neural network evolution

    Publication Year: 2000, Page(s):585 - 590 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (481 KB)

    In this study a new evolutionary algorithm, i.e., representative evolution (RE), for evolving artificial neural networks (ANN) is proposed. Unlike most of the evolutionary algorithms, the RE uses population information for generating variations in individuals of a population. An evolutionary system, i.e., RENet, based on the RE for evolving feedforward artificial neural networks with weight learni... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 4th International Conference on Adhesive Joining and Coating Technology in Electronics Manufacturing. Proceedings. Presented at Adhesives in Electronics 2000 (Cat. No.00EX431)

    Publication Year: 2000
    Request permission for commercial reuse | PDF file iconPDF (689 KB)
    Freely Available from IEEE
  • Author index

    Publication Year: 2000, Page(s):649 - 659
    Request permission for commercial reuse | PDF file iconPDF (761 KB)
    Freely Available from IEEE
  • Applying synaptic delays for virtual sensing and actuation in mobile robots

    Publication Year: 2000, Page(s):144 - 149 vol.6
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (572 KB)

    In this article we describe the use of Artificial Neural Networks (ANN) with synaptic time delays between the nodes as a means to increase the capabilities of the usual control modules used in behavior based robotics. This inclusion allows the controllers to manage explicit temporal information in different levels. In the sensing level it permits the use of virtual sensors that improve the precisi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Study of a sequence of neural oscillators

    Publication Year: 2000, Page(s):429 - 433 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (348 KB)

    We present the study of the behavior of an homogeneous linear array of two neural oscillators, with the objective of determining the characteristics of the oscillatory state of the circuit, as well as the effect of some of the parameters of the circuit on the oscillatory behavior. We show the different responses that can be obtained from this kind of circuits View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Morphological neural networks for robust visual processing in mobile robotics

    Publication Year: 2000, Page(s):140 - 143 vol.6
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (204 KB)

    Morphological Neural Networks (MNN) have been proposed as associative (with its two cases: autoassociative and heteroassociative) memories. In this paper we are involved with Heteroassociative MNN (HMNN). We propose their utilization as a preprocessing step for human shape detection, in a vision-based navigation problem for mobile robots. MNN can be trained in a single computing step, they possess... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bayesian neural network for fermentation control

    Publication Year: 2000, Page(s):279 - 284 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (464 KB)

    This paper illustrates the potentiality of Bayesian neural networks to model the concentration of the antibiotic cephalosporin in a fermentator from the estimate of the control variables. We show that our models give satisfactory results together with an estimate of the uncertainty associated to each prediction, allowing a potential operator to deal with anomalies during the process. The determina... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bifurcating pulsed neural networks, chaotic neural networks and parametric recursions: conciliating different frameworks in neuro-like computing

    Publication Year: 2000, Page(s):423 - 428 vol.6
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (364 KB)

    This paper addresses the concept of parametric recursions in the context of neuro-like architectures and relates it to different classes of neural networks, including pulsed models and chaotic neural networks. It also addresses the contrast between the dynamical states exhibited by networks of parametric recursive elements and the fixed point attractors used in traditional neural networks, as well... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evolving neural network structures using axonal growth mechanisms

    Publication Year: 2000, Page(s):591 - 595 vol.6
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (316 KB)

    In the field of artificial evolution creating methods to evolve neural networks is an important goal. But how to encode the structure and properties of the neural network in the genome is still a problem. If one overloads the genome with detailed information for a network the evolutionary time increases prohibitively. If the genome is too simple, only simple problems can be solved. As Nature has f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hypersphere ART and ARTMAP for unsupervised and supervised, incremental learning

    Publication Year: 2000, Page(s):59 - 64 vol.6
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (420 KB)

    A novel adaptive resonance theory (ART) neural network architecture is being proposed. The new model, called Hypersphere ART (H-ART) is based on the same principals as Fuzzy-ART and, thus, inherits most of its qualities for unsupervised learning. Among these properties is fast, stable, incremental learning on the training set and good generalization on the testing set. While H-ART is intended for ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Uncertainty of the short-term electrical load forecasting in utilities

    Publication Year: 2000, Page(s):235 - 240 vol.6
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (396 KB)

    This paper investigates the problem of the short-term electrical load forecasting (STLF) in medium size utility. The model consisted of ensemble of the neural predictors with special heuristic input selection procedure is presented. We also discuss the problem of uncertainties involved in load forecasts, and confidence intervals calculation methods for neural STLF predictors View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust visual recognition with high-order Gaussian synapses networks

    Publication Year: 2000, Page(s):135 - 139 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (388 KB)

    In the context of visual systems for robots, we have made use of a high order gaussian synapses network and the Gaussian Synapses Backpropagation Algorithm (GSBP) for the implementation of the detectors that constitute one part of the whole visual architecture. These detectors are trained to be sensitive to spatial patterns that are relevant for the decisions the robot must perform during its oper... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A noise-robust front-end based on tree-structured filter-bank for speech recognition

    Publication Year: 2000, Page(s):81 - 86 vol.6
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (536 KB)

    This paper presents a new model of auditory preprocessors based on tree structured filter-banks to provide the robustness to noise and the ease of hardware implementation. The robustness to noise is further improved by two components: one is the adaptive Q control of filter-bank in the sense of enhancing the contrast between frequency channels and another is the adaptive gain control of filter-ban... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A hierarchical neural network-based approach to VIRGO noise identification

    Publication Year: 2000, Page(s):253 - 258 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (292 KB)

    In this paper a hierarchical neural network-based approach is presented to identify the noise in the VIRGO experiment to detect gravitational waves by means of a laser interferometer View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Text independent speaker verification using modular neural network

    Publication Year: 2000, Page(s):97 - 102 vol.6
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (212 KB)

    This work addresses the data balancing problem of the existing neural network based speaker verification methods, and proposes new method using modular neural network. In this method, each expert network is trained with the balanced number of genuine speaker data and imposter speaker data. In our experiments, we obtained high performance results for the unknown imposter speakers. High performance ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new method for tracking modulations in tonal music in audio data format

    Publication Year: 2000, Page(s):270 - 275 vol.6
    Cited by:  Papers (6)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (428 KB)

    Cq-profiles are 12-dimensional vectors, each component referring to a pitch class. They can be employed to represent keys. Cq-profiles are calculated with the constant Q filter bank. They have the following advantages: 1) they correspond to probe tone ratings; 2) calculation is possible in real-time; 3) stability is obtained with respect to sound quality; and 4) they are transposable. By using the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computational intelligence in adaptive educational hypermedia

    Publication Year: 2000, Page(s):629 - 634 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (508 KB)

    In this paper neuro-fuzzy synergism is applied to implement content sequencing in adaptive hypermedia systems. The level of understanding of the learner is used to construct lessons adapted to the learner's knowledge goals and level of expertise on the domain concepts s/he has already studied. The learner's evaluation is based on defining appropriate fuzzy sets and relate learner's response with a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Randomly connected neural networks displaying 1/f spectra

    Publication Year: 2000, Page(s):419 - 422 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (180 KB)

    It is known that electroencephalogram (EEG) is broadly scale-invariant over several orders of frequencies. Applying the renormalization group method to the neural network model, we obtain the self-similar solution from which the scaling exponent -1 of the spectrum fall-off. This paper permits one to study the self-similar behavior and helps in understanding the basic ingredients underlying 1/f spe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Classification of noisy signal using fuzzy ARTMAP neural networks

    Publication Year: 2000, Page(s):53 - 58 vol.6
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (640 KB)

    This paper describes an approach to classification of noisy signals using a technique based on the Fuzzy ARTMAP neural network (FAM). A variation of the testing phase of Fuzzy ARTMAP is introduced, that exhibited superior generalization performance than the standard Fuzzy ARTMAP in the presence of noise. We present an application of our technique for textured grayscale images. We perform a large n... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • GA-based supervised learning of Neocognitron

    Publication Year: 2000, Page(s):559 - 564 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (312 KB)

    Supervised learning of Neocognitron is fulfilled by presenting training patterns, which map to specified features. However, the training patterns and many parameters are designed empirically and set manually in Fukushima's Neocognitron. In this paper, we use genetic algorithms (GAs) to tune the parameters of Neocognitron and search its reasonable training pattern sets. First of all, the correlatio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Role of artificial neural networks and wavelets in online reliability monitoring of physical systems

    Publication Year: 2000, Page(s):369 - 374 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (456 KB)

    In some cases, degradation signals exhibited by a physical component contain valuable information regarding the state or well-being of the component. We introduce several methods that facilitate estimation of individual component reliability utilizing online degradation signals. Even though degradation signals can be modeled using different tools, the paper discusses the relevance of neural networ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neuro-fuzzy approaches to short-term electrical load forecasting

    Publication Year: 2000, Page(s):229 - 234 vol.6
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (256 KB)

    We investigate the application of the Takagi-Sugeno fuzzy models to short-term electrical load forecasting problem. Several learning algorithms for these type fuzzy systems are discussed. For identification of the models with linear antecedents the combination of the cluster estimation and ordinary least squares method are applied. For nonlinear antecedent modelling purposes the fuzzy switched ens... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Increased robustness in visual processing with SOM-based filtering

    Publication Year: 2000, Page(s):131 - 134 vol.6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (212 KB)

    To increase the robustness of visual processing in the context of mobile robotics, we introduce an image filtering process based on the codebooks computed by the SOM. The Self Organizing Map and the Simple Competitive Learning are used to compute adaptively the vector quantizers of color image sequences. The codebook computed for each image in the sequence is then used as a smoothing filter, the V... View full abstract»

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