Name
Title | ||
|---|---|---|
Designing simple nonlinear filters using hysteresis of single recurrent neurons for acoustic signal recognition in robots |
Abstract | ||
|---|---|---|
In this article we exploit the discrete-time dynamics of a single neuron with self-connection to systematically design simple signal filters. Due to hysteresis effects and transient dynamics, this single neuron behaves as an adjustable low-pass filter for specific parameter configurations. Extending this neuro-module by two more recurrent neurons leads to versatile high- and band-pass filters. The approach presented here helps to understand how the dynamical properties of recurrent neural networks can be used for filter design. Furthermore, it gives guidance to a new way of implementing sensory preprocessing for acoustic signal recognition in autonomous robots. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1007/978-3-642-15819-3_50 | ICANN (1) |
Keywords | Field | DocType |
filter design,single recurrent neuron,recurrent neuron,discrete-time dynamic,autonomous robot,single neuron,simple nonlinear filter,recurrent neural network,band-pass filter,acoustic signal recognition,design simple signal filter,adjustable low-pass filter,nonlinear filter,discrete time,neural networks,band pass filter,low pass filter,neural network,digital signal processing | Digital signal processing,Nonlinear system,Control theory,Computer science,Recurrent neural network,Preprocessor,Robot,Artificial neural network,Autonomous robot,Filter design | Conference |
Volume | ISSN | ISBN |
6352 | 0302-9743 | 3-642-15818-8 |
Citations | PageRank | References |
2 | 0.37 | 10 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Poramate Manoonpong | 1 | 94 | 11.02 |
| Frank Pasemann | 2 | 263 | 27.70 |
| Christoph Kolodziejski | 3 | 92 | 8.60 |
| Florentin Wörgötter | 4 | 1304 | 119.30 |