Augmentation of Training and Performance Analysis through Fuzzy-Logic and Neural Network
Keywords:
Neural Networks, Fuzzy Rationale Controlled Neural NetworkAbstract
One significant issue in the utilization of artificial neural networks is the long preparing time. The reason for this paper is to show the advancement of preparing that happens with the utilization of fuzzy rationale controller hypothesis to artificial neural networks. The subsequent fuzzy rationale controlled neural network (FRCNN) shows a noteworthy cut in the preparation time frame. A fuzzy rationale system (FLS) is utilized to control the learning parameters of neural networks (NN) to diminish the chance of overshooting during the learning procedure. Thus, the learning time of the neural network can be abbreviated. This paper looks at the preparation effectiveness and precision between a NN and a FLCNN, when they are required to complete a similar task. In one application, the preparation time is decreased by 30%.
References
- Abduladheem A et al. [2005]: Hybrid wavelet-network neural /FFT neural phoneme recognition. Proceedings of the 2nd International Conference on Information Technology, Al- Zaytoonah University of Jordan.
- Agarwal KK et al. [2004]:A neural net-based approach to test oracle. ACM SIGSOFT, 29, 1-6.
- Dokur Z et al. [2003]: Classification of respiratory sounds by using an artificial neural network. International Journal of Pattern Recognition and Artificial Intelligence, 4, 567-580.
- Downton A et al. [1997]: In progress in handwriting recognition. World Scientific, UK.
- Erik Hjelmas et al. [2001]: Face Detection A Survey Department of Informatics. University of Oslo, Norway.
- Farrel K R et al. [1994]:Speaker recognition using neural networks and conventional classifiers. IEE Trans., on Speech and Audio Proc., 194-205.
- Fok S et al. [2001]: Feature-Based component models for virtual prototyping of hydraulic systems. The International Journal of Advanced Manufacturing Technology, 18, 665-672.
- Franzini MA et al. [1987]:Speech recognition with back propagation. Proceedings of the IEEE/Ninth Annual Conference of the Engineering in Medicine and Biology Society, Boston, MA, 9, 1702-1703.
- Holt et al. [1990]: Convergence of back propagation in neural networks using a log-likelihood cost function. Electron Letters, 26, 1964-1965.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRST
This work is licensed under a Creative Commons Attribution 4.0 International License.
