WSOM: building adaptive wavelets with self-organizing maps
Marcos M. Campos, Gail A. Carpenter · 2002
The WSOM (wavelet self-organizing map) model, a neural network for the creation of wavelet bases adapted to the distribution of input data, is introduced. The model provides an efficient online method to construct high-dimensional wavelet bases. Simulations of a 1D function approximation problem illustrate how WSOM adapts to non-uniformly distributed input data, outperforming the discrete wavelet transform. A speaker-independent vowel recognition benchmark task demonstrates how the model constructs high-dimensional bases using low-dimensional wavelets.