BookDOI
Advances in Neural Networks – ISNN 2007
TLDR
In this article, the authors apply harmony data smoothing learning on a weighted kernel density model to obtain a sparse density estimator and empirically compare this method with the least squares cross-validation (LSCV) method for the classical kernel density estimators.Abstract:
In this paper we apply harmony data smoothing learning on a weighted kernel density model to obtain a sparse density estimator. We empirically compare this method with the least squares cross-validation (LSCV) method for the classical kernel density estimator. The most remarkable result of our study is that the harmony data smoothing learning method outperforms LSCV method in most cases and the support vectors selected by harmony data smoothing learning method are located in the regions of local highest density of the sample.read more
Citations
More filters
Book ChapterDOI
Sequential deep learning for human action recognition
TL;DR: A fully automated deep model, which learns to classify human actions without using any prior knowledge is proposed, which outperforms existing deep models, and gives comparable results with the best related works.
Book ChapterDOI
An Interval Type-2 Fuzzy Neural Network for Chaotic Time Series Prediction with Cross-Validation and Akaike Test
TL;DR: A novel homogeneous integration strategy of an interval type-2 fuzzy inference system (IT2FIS) with Takagi-Sugeno-Kang reasoning (TSK IT2FLS) is presented and soundness for uncertainty, adaptability and learning and generalization capabilities is shown.
Journal ArticleDOI
Microwave irradiation pretreatment and peroxyacetic acid desulfurization of coal and application of GRNN simultaneous predictor
S. Chehreh Chelgani,E. Jorjani +1 more
TL;DR: In this article, an Artificial Neural Network (ANN) was used to predict the effects of operational parameters on coal desulfurization using peroxyacetic acid from microwave pretreated coal.
Book ChapterDOI
Image segmentation fusion using general ensemble clustering methods
TL;DR: It is shown that the ensemble clustering approach yields results close to the supervised learning, but without any ground truth information.
Journal ArticleDOI
Modeling of oxygen mass transfer in the presence of oxygen-vectors using neural networks developed by differential evolution algorithm
TL;DR: Two variants of the Differential Evolution algorithm were used to obtain the best neural networks in two distinct cases: for prediction and classification problems, proving that the neural network based modeling is an appropriate technique and the DE algorithm is able to lead to the near-optimal neural network topology.
References
More filters
BookDOI
Handbook of Face Recognition
Stan Z. Li,Anil K. Jain +1 more
TL;DR: This highly anticipated new edition provides a comprehensive account of face recognition research and technology, spanning the full range of topics needed for designing operational face recognition systems, as well as offering challenges and future directions.
Journal ArticleDOI
PCNN models and applications
John L. Johnson,Mary Lou Padgett +1 more
TL;DR: The linking field modulation term is shown to be a universal feature of any biologically grounded dendritic model and the PCNN image decomposition (factoring) model is described in new detail.
Journal ArticleDOI
Perfect image segmentation using pulse coupled neural networks
G. Kuntimad,Heggere S. Ranganath +1 more
TL;DR: Conditions for perfect image segmentation are derived and it is shown that addition of an inhibition receptive field to the neuron model increases the possibility of perfect segmentation.
Journal ArticleDOI
Pulse-coupled neural nets: translation, rotation, scale, distortion, and intensity signal invariance for images
TL;DR: The linking-field neural network model was introduced to explain the experimentally observed synchronous activity among neural assemblies in the cat cortex induced by feature-dependent visual activity and gives a basic new function: grouping by similarity.
Book
Image processing using pulse-coupled neural networks
TL;DR: This volume provides an introduction to the topic by reviewing the theoretical foundations as well as a number of image processing applications, including segmentation, edge extraction, texture extraction, object identification, object isolation, motion processing, noise suppression, and image fusion.
Related Papers (5)
Scalable Wide Neural Network: A Parallel, Incremental Learning Model Using Splitting Iterative Least Squares
A pruning algorithm of neural networks using impact factor regularization
Hajoon Lee,Cheol Hoon Park +1 more