A recurrent neural network-based method for training probabilistic Support Vector Machine
Year
: 2009
Abstract: In this paper, Support Vector Machine (SVM) is reformulated to a recurrent neural
network model which can be described by the nonlinear dynamic system. In the proposed
algorithm, an iterative training procedure is proposed independent of initial point. Also
probabilistic constraints are recommended for reducing effect of noisy samples in training
procedure and appearance of incorrect Support Vectors (SV). Probabilistic constraints admit
using knowledge about distribution function of samples. A set of differential equations is used
to modelling of the proposed probabilistic SVM. These equations are converged to optimal
solution for SVM. The Euler method is used to solve differential equation. The primal and
dual problem of SVM is solved by this model. Enough information is given for finding
optimal hyper plane. Capability of the proposed method is shown by experimental results in the
Optical Character Recognition (OCR) and synthetic data.
network model which can be described by the nonlinear dynamic system. In the proposed
algorithm, an iterative training procedure is proposed independent of initial point. Also
probabilistic constraints are recommended for reducing effect of noisy samples in training
procedure and appearance of incorrect Support Vectors (SV). Probabilistic constraints admit
using knowledge about distribution function of samples. A set of differential equations is used
to modelling of the proposed probabilistic SVM. These equations are converged to optimal
solution for SVM. The Euler method is used to solve differential equation. The primal and
dual problem of SVM is solved by this model. Enough information is given for finding
optimal hyper plane. Capability of the proposed method is shown by experimental results in the
Optical Character Recognition (OCR) and synthetic data.
Keyword(s): recurrent neural network model,differential equation,probabilistic constraints,SVC,
support vector machine,OCA,optical character recognition
Collections
:
-
Statistics
A recurrent neural network-based method for training probabilistic Support Vector Machine
Show full item record
| contributor author | هادی صدوقی یزدی | en |
| contributor author | سهراب عفتی | en |
| contributor author | Z.Saberi | en |
| contributor author | Hadi Sadoghi Yazdi | fa |
| contributor author | Sohrab Effati | fa |
| date accessioned | 2020-06-06T14:08:50Z | |
| date available | 2020-06-06T14:08:50Z | |
| date issued | 2009 | |
| identifier uri | https://libsearch.um.ac.ir:443/fum/handle/fum/3384352?locale-attribute=en | |
| description abstract | In this paper, Support Vector Machine (SVM) is reformulated to a recurrent neural network model which can be described by the nonlinear dynamic system. In the proposed algorithm, an iterative training procedure is proposed independent of initial point. Also probabilistic constraints are recommended for reducing effect of noisy samples in training procedure and appearance of incorrect Support Vectors (SV). Probabilistic constraints admit using knowledge about distribution function of samples. A set of differential equations is used to modelling of the proposed probabilistic SVM. These equations are converged to optimal solution for SVM. The Euler method is used to solve differential equation. The primal and dual problem of SVM is solved by this model. Enough information is given for finding optimal hyper plane. Capability of the proposed method is shown by experimental results in the Optical Character Recognition (OCR) and synthetic data. | en |
| language | English | |
| title | A recurrent neural network-based method for training probabilistic Support Vector Machine | en |
| type | Journal Paper | |
| contenttype | External Fulltext | |
| subject keywords | recurrent neural network model | en |
| subject keywords | differential equation | en |
| subject keywords | probabilistic constraints | en |
| subject keywords | SVC | en |
| subject keywords | support vector machine | en |
| subject keywords | OCA | en |
| subject keywords | optical character recognition | en |
| journal title | International Journal of Signal and Imaging Systems Engineering-IJSISE | fa |
| pages | 57-65 | |
| journal volume | 2 | |
| journal issue | 1 | |
| identifier link | https://profdoc.um.ac.ir/paper-abstract-1012475.html | |
| identifier articleid | 1012475 |