Translator Disclaimer
Paper
16 September 1992 Modified backpropagation neural network with applications to image compression
Author Affiliations +
Abstract
The back-propagation neural network algorithm is an iterative technique for learning the relationship between an input and output. This algorithm has been successfully used in many real-world applications; however, it suffers from slow convergence problems and can get struck in local minima of the weight-error surface. A generalization of previously proposed activation functions has been developed using a free parameter for improved convergence. A modified algorithm based on these function is suggested by bounding the input data to the derivative evaluation in the backwards pass. The modified algorithm has demonstrated superior performance on the standard parity and encoder problems. Finally, a histogram normalization technique is presented for image data compression for improved convergence.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Surender K. Kenue "Modified backpropagation neural network with applications to image compression", Proc. SPIE 1709, Applications of Artificial Neural Networks III, (16 September 1992); https://doi.org/10.1117/12.140017
PROCEEDINGS
14 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Variable-rate predictive residual vector quantization
Proceedings of SPIE (April 21 1995)
Competitive learning algorithms for image coding
Proceedings of SPIE (September 16 1992)
Image compression and SANN equations
Proceedings of SPIE (September 02 1993)

Back to Top