Advances in Neural Networks – ISNN 2012: 9th International by Alexander A. Frolov, Dušan Húsek, Pavel Yu. Polyakov

By Alexander A. Frolov, Dušan Húsek, Pavel Yu. Polyakov (auth.), Jun Wang, Gary G. Yen, Marios M. Polycarpou (eds.)

The two-volume set LNCS 7367 and 7368 constitutes the refereed complaints of the ninth foreign Symposium on Neural Networks, ISNN 2012, held in Shenyang, China, in July 2012. The 147 revised complete papers offered have been conscientiously reviewed and chosen from a number of submissions. The contributions are dependent in topical sections on mathematical modeling; neurodynamics; cognitive neuroscience; studying algorithms; optimization; trend attractiveness; imaginative and prescient; snapshot processing; details processing; neurocontrol; and novel applications.

Show description

Read or Download Advances in Neural Networks – ISNN 2012: 9th International Symposium on Neural Networks, Shenyang, China, July 11-14, 2012. Proceedings, Part I PDF

Similar networks books

Computer Networks (4th Edition) - Problem Solutions

Entire suggestions for computing device Networks (4th variation) by means of Andrew Tanenbaum.

Advances in Neural Networks - ISNN 2010: 7th International Symposium on Neural Networks, ISNN 2010, Shanghai, China, June 6-9, 2010, Proceedings, Part I

This booklet and its sister quantity acquire refereed papers awarded on the seventh Inter- tional Symposium on Neural Networks (ISNN 2010), held in Shanghai, China, June 6-9, 2010. development at the luck of the former six successive ISNN symposiums, ISNN has turn into a well-established sequence of well known and high quality meetings on neural computation and its functions.

Sensor Networks and Configuration: Fundamentals, Standards, Platforms, and Applications

Advances in networking effect many varieties of tracking and regulate platforms within the such a lot dramatic approach. Sensor community and configuration falls less than the class of recent networking platforms. instant Sensor community (WSN) has emerged and caters to the necessity for real-world functions. technique and layout of WSN represents a huge learn subject with functions in lots of sectors corresponding to undefined, domestic, computing, agriculture, setting, etc, according to the adoption of primary ideas and the cutting-edge know-how.

Extra info for Advances in Neural Networks – ISNN 2012: 9th International Symposium on Neural Networks, Shenyang, China, July 11-14, 2012. Proceedings, Part I

Sample text

Although this method can obtain best feature sub-set, it is time-consuming, especially for high dimensional spectral data. Therefore, a simple method based on MIFS was proposed in [6]. It is used in here: given a threshold value of the MI, if the MI values of the features are higher than threshold value, it is selected. However, how to select the optimal threshold value is a difficulty problem. 2 Nonlinear Modeling Based on Kernel ELM ELM was originally proposed for the single-hidden layer feed forward networks (SLFNs) [7,10] and then extended to the generalized single-hidden layer feed forward network [11,12].

Thus for the criterion function F, we have a Lipschitz constant of 1 2  LF =  max   (t pk − o pk ) 2   Lok . p  k  k (4) Extension of the procedure to estimating a Lipschitz constant for an FNN with more than one hidden layer can be carried out by applying the basic lemmas recursively, as illustrated above. 4 Computing Local Lipschitz Constant The procedures outlined in Section 3 allow us to easily compute Lipschitz constant over subsets of the weight space. For clarity of exposition, we will consider computing the Lipschitz constant of a three layer FNN with a single output unit.

More simulations will be done to validate this approach further. Acknowledgments. 20100471464). References 1. : Unsupervised Linear Feature-Extraction Methods and Their Effects in the Classification of High-Dimensional Data. IEEE Transaction on Geoscience and Remote Sensing 45, 469–483 (2007) 2. : Feature Selection with Kernel Class Separability. IEEE Transactions on Pattern Analysis and Machine Intelligence 30, 1534–1546 (2008) 3. : Variable Selection for Multivariate Calibration Using a Genetic Algorithm: Prediction of Additive Concentrations in Polymer Films from Fourier Transform-infrared Spectral Data.

Download PDF sample

Rated 4.84 of 5 – based on 14 votes