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. Key words: Neural networks, Digital signal processing, Non-speech recognition, Autonomous robots, Walking robots

• Type: Conference
• Year: 2010
• Where: ICANN
• Authors: Poramate Manoonpong, Frank Pasemann, Christoph Kolodziejski, Florentin Wörgötter
• Keywords: Autonomous Robots, ICANN 2010, Neural Networks, Single Neuron