Abstract
The demonstration of the limitations of single-layer neural networks was a significant factor in the decline of interest in neural networks in the 1970s. The discovery (by several researchers independently) and widespread dissemination of an effective general method of training a multilayer neural network (Rumelhart, Hinton, & Williams, 1986a, 1986b; McClelland & Rumelhart, 1988) played a major role in the re-emergence of neural networks as a tool for solving a wide variety of problems. The training of a network by back-propagation involves three stages: the feedforward of the input training pattern, the calculation and back-propagation of the associated error, and the adjustment of the weights. After training, application of the net involves only the computations of the feedforward phase. Even if training is slow, a trained net can produce its output very rapidly. Numerous variations of backpropagation have been developed to improve the speed of the training process.
Metadata
Item Type: | Thesis (Degree) |
---|---|
Creators: | Creators Email / ID Num. Mohammad Arif, Mazneeda 2008740667 |
Contributors: | Contribution Name Email / ID Num. Thesis advisor Shamsuddin, Razif UNSPECIFIED |
Subjects: | Q Science > QA Mathematics > Instruments and machines > Electronic Computers. Computer Science > Neural networks (Computer science) T Technology > TA Engineering. Civil engineering > Applied optics. Photonics > Optical pattern recognition > Human face recognition (Computer science) |
Divisions: | Universiti Teknologi MARA, Shah Alam > Faculty of Computer and Mathematical Sciences |
Programme: | Bachelor of Computer Science (Hons) |
Keywords: | Eye recognition, shapes of eye, speed of training process |
Date: | 2010 |
URI: | https://ir.uitm.edu.my/id/eprint/65808 |
Download
65808.pdf
Download (113kB)