Results 21 to 30 of about 66,291 (256)

New Directions in Data Analysis [PDF]

, 2001
In the next decade, high energy physicists will use very sophisticated equipment to record unprecedented amounts of data in the hope of making major advances in our understanding of particle phenomena.
Bhat, Pushpalatha C.
core   +2 more sources

A wavelet neural network for the approximation of nonlinear multivariable function

IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028), 2000
Wavelet neural networks employing the wavelet function as the activation function have been proposed previously as an alternative approach to nonlinear mapping problems. In this paper, we propose a wavelet neural network which can be employed as a useful tool for learning a mapping between an input and an output space.
Ting Wang, Yasuo Sugai
openaire   +2 more sources

Estimation of Approximating Rate for Neural Network inLwp Spaces

Journal of Applied Mathematics, 2012
A class of Soblove type multivariate function is approximated by feedforward network with one hidden layer of sigmoidal units and a linear output. By adopting a set of orthogonal polynomial basis and under certain assumptions for the governing activation
Jian-Jun Wang, Chan-Yun Yang, Jia Jing
doaj   +1 more source

Theoretical Properties of Projection Based Multilayer Perceptrons with Functional Inputs [PDF]

, 2006
Many real world data are sampled functions. As shown by Functional Data Analysis (FDA) methods, spectra, time series, images, gesture recognition data, etc.
A. R. Barron, B. A. Brumback, Brieuc Conan-Guez, C. Abraham, D. R. Hoover, F. Ferraty, F. Rossi, F. Rossi, F. Rossi, Fabrice Rossi, G. Biau, G. Lugosi, G. M. James, G. M. James, G. M. James, G. M. James, H. Cardot, H. Cardot, H. Luschgy, H. White, I. W. Sandberg, I. W. Sandberg, I. W. Sandberg, J. A. Rice, J. Dauxois, J. Dauxois, J. Deville, J. O. Ramsay, L. Ferré, M. B. Stinchcombe, P. Besse, P. Besse, S. Leurgans, T. Chen, T. Chen, T. Chen, T. Chen, T. Hastie, T. Hastie   +38 more
core   +5 more sources

The errors of simultaneous approximation of multivariate functions by neural networks

Computers & Mathematics with Applications, 2011
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Tingfan Xie, Feilong Cao
openaire   +1 more source

Design Issues and Challenges of File Systems for Flash Memories [PDF]

, 2011
This chapter discusses how to properly address the issues of using NAND flash memories as mass-memory devices from the native file system standpoint. We hope that the ideas and the solutions proposed in this chapter will be a valuable starting point for ...
Cramia, M., Di Carlo, Stefano, Fabiano, Michele, Prinetto, Paolo Ernesto   +3 more
core   +2 more sources

Neural Likelihoods via Cumulative Distribution Functions [PDF]

, 2020
We leverage neural networks as universal approximators of monotonic functions to build a parameterization of conditional cumulative distribution functions (CDFs). By the application of automatic differentiation with respect to response variables and then
Chilinski, Pawel, Silva, Ricardo
core   +1 more source

Approximation of empowerment in the continuous domain [PDF]

, 2012
The empowerment formalism offers a goal-independent utility function fully derived from an agent's embodiment. It produces intrinsic motivations which can be used to generate self-organizing behaviours in agents.
Glackin, Cornelius, Polani, D., Salge, Christoph   +2 more
core   +1 more source

An improved adaptive neuro fuzzy inference system model using conjoined metaheuristic algorithms for electrical conductivity prediction

Scientific Reports, 2022
Precise prediction of water quality parameters plays a significant role in making an early alert of water pollution and making better decisions for the management of water resources.
Iman Ahmadianfar, Seyedehelham Shirvani-Hosseini, Jianxun He, Arvin Samadi-Koucheksaraee, Zaher Mundher Yaseen   +4 more
doaj   +1 more source

Multivariate Smooth Symmetrized and Perturbed Hyperbolic Tangent Neural Network Approximation over Infinite Domains

Mathematics
In this article, we study the multivariate quantitative smooth approximation under differentiation of functions. The approximators here are multivariate neural network operators activated by the symmetrized and perturbed hyperbolic tangent activation ...
George A. Anastassiou
doaj   +1 more source