Circular backpropagation networks embed vector quantization
- 1 July 1999
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 10 (4) , 972-975
- https://doi.org/10.1109/72.774275
Abstract
This letter proves the equivalence between vector quantization (VQ) classifiers and circular backpropagation (CBP) networks. The calibrated prototypes for a VQ schema can be plugged in a CBP feedforward structure having the same number of hidden neurons and featuring the same mapping. The letter describes how to exploit such equivalence by using VQ prototypes to perform a meaningful initialization for BP optimization. The approach effectiveness was tested considering a real classification problem (NIST handwritten digits).Keywords
This publication has 8 references indexed in Scilit:
- Density-based clustering with topographic mapsIEEE Transactions on Neural Networks, 1999
- Kernel-Based Equiprobabilistic Topographic Map FormationNeural Computation, 1998
- Plastic algorithm for adaptive vector quantisationNeural Computing & Applications, 1998
- Circular backpropagation networks for classificationIEEE Transactions on Neural Networks, 1997
- An Adaptive Momentum Back Propagation (AMBP)Neural Computing & Applications, 1995
- Multifunctional hybrid neural netNeural Networks, 1992
- Self-Organization and Associative MemoryPublished by Springer Nature ,1989
- An Algorithm for Vector Quantizer DesignIEEE Transactions on Communications, 1980