A Digital Antennal Lobe for Pattern Equalization: Analysis and Design

Abstract

Re-mapping patterns in order to equalize their distribution may greatly simplify both the structure and the training of classifiers. Here, the properties of one such map obtained by running a few steps of discrete-time dynamical system are explored. The system is called 'Digital Antennal Lobe' (DAL) because it is inspired by recent studies of the antennallobe, a structure in the olfactory sys(cid:173) tem of the grasshopper. The pattern-spreading properties of the DAL as well as its average behavior as a function of its (few) de(cid:173) sign parameters are analyzed by extending previous results of Van Vreeswijk and Sompolinsky. Furthermore, a technique for adapting the parameters of the initial design in order to obtain opportune noise-rejection behavior is suggested. Our results are demonstrated with a number of simulations.

Cite

Text

Holub et al. "A Digital Antennal Lobe for Pattern Equalization: Analysis and Design." Neural Information Processing Systems, 2002.

Markdown

[Holub et al. "A Digital Antennal Lobe for Pattern Equalization: Analysis and Design." Neural Information Processing Systems, 2002.](https://mlanthology.org/neurips/2002/holub2002neurips-digital/)

BibTeX

@inproceedings{holub2002neurips-digital,
  title     = {{A Digital Antennal Lobe for Pattern Equalization: Analysis and Design}},
  author    = {Holub, Alex and Laurent, Gilles and Perona, Pietro},
  booktitle = {Neural Information Processing Systems},
  year      = {2002},
  pages     = {245-253},
  url       = {https://mlanthology.org/neurips/2002/holub2002neurips-digital/}
}