Circular backpropagation networks embed vector quantization

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).

[1]  David Casasent,et al.  Multifunctional hybrid neural net , 1992, Neural Networks.

[2]  Marc M. Van Hulle.  Density-based clustering with topographic maps , 1999, IEEE Trans. Neural Networks.

[3]  M. Hulle.  Kernel-Based Equiprobabilistic Topographic Map Formation , 1998, Neural Computation.

[4]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory, Third Edition , 1989, Springer Series in Information Sciences.

[5]  Sandro Ridella,et al.  Circular backpropagation networks for classification , 1997, IEEE Trans. Neural Networks.

[6]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..