A Digital Antennal Lobe for Pattern Equalization: Analysis and Design
- Creators
- Holub, Alex
-
Laurent, Gilles
-
Perona, Pietro
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 system of the grasshopper. The pattern-spreading properties of the DAL as well as its average behavior as a function of its (few) design 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.
Additional Information
© 2003 Massachusetts Institute of Technology. We would like to thank Or Neeman for useful suggestions and feedback. This work was supported in part by the Engineering Research Centers Program of the National Science Foundation under Award Number EEC-9402726.Attached Files
Published - 2243-a-digital-antennal-lobe-for-pattern-equalization-analysis-and-design.pdf
Files
| Name | Size | Download all |
|---|---|---|
|
md5:531e800472b60b0e5daaf822d2629593
|
1.5 MB | Preview Download |
Additional details
- Eprint ID
- 64881
- Resolver ID
- CaltechAUTHORS:20160229-163959280
- NSF
- EEC-9402726
- Created
-
2016-03-09Created from EPrint's datestamp field
- Updated
-
2019-10-03Created from EPrint's last_modified field
- Series Name
- Advances in Neural Information Processing Systems
- Series Volume or Issue Number
- 15