Designing Simple Nonlinear Filters Using Hysteresis of Single Recurrent Neurons for Acoustic Signal Recognition in Robots
| Autor: | Frank Pasemann, Poramate Manoonpong, Florentin Wörgötter, Christoph Kolodziejski |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
Quantitative Biology::Neurons and Cognition
Artificial neural network business.industry Computer science 02 engineering and technology Filter (signal processing) Autonomous robot Signal 03 medical and health sciences Filter design Hysteresis Nonlinear system 0302 clinical medicine Recurrent neural network Control theory 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing business 030217 neurology & neurosurgery Digital signal processing |
| Zdroj: | Artificial Neural Networks – ICANN 2010 ISBN: 9783642158186 ICANN (1) |
| DOI: | 10.1007/978-3-642-15819-3_50 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|