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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Dayhoff, J.E., Palmadesso, P.J., Richards, F.: Oscillation Responses in a Chaotic Recurrent Network. In: Recurrent Neural Networks: Design and Applications, pp. 153–177. CRC Press, Boca Raton (1999)
Steingrube, S., Timme, M., Wörgötter, F., Manoonpong, P.: Self-Organized Adaptation of a Simple Neural Circuit Enables Complex Robot Behaviour. Nature Physics 6, 224–230 (2010)
Ziemke, T.: On Parts and Wholes of Adaptive Behavior: Functional Modularity and Dichronic Structure in Recurrent Neural Robot Controllers. In: 6th International Conference on Simulation of Adaptive Behavior, pp. 115–124 (2000)
Zegers, P., Sundareshan, M.K.: Trajectory Generation and Modulation using Dynamic Neural Networks. IEEE T. Neural Networ. 14(3), 520–533 (2003)
Hülse, M., Wischmann, S., Pasemann, F.: Structure and Function of Evolved Neuro-Controllers for Autonomous Robots. Connect. Sci. 16(4), 249–266 (2004)
Williams, R.J., Peng, J.: An Efficient Gradient–Based Algorithm for On–Line Training of Recurrent Network Trajectories. Neural Comput. 2(4), 490–501 (1990)
Becerikli, Y.: Nonlinear Filtering Design using Dynamic Neural Networks with Fast Training. In: Yazıcı, A., Şener, C. (eds.) ISCIS 2003. LNCS, vol. 2869, pp. 601–610. Springer, Heidelberg (2003)
Hagen, M.T., De Jesus, O., Schultz, R.: Training Recurrent Networks for Filtering and Control. In: Recurrent Neural Networks: Design and Applications, pp. 325–354. CRC Press, Boca Raton (1999)
Squartini, S., Cecchi, S., Rossini, M., Piazza, F.: Echo State Networks for Real-Time Audio Applications. In: Liu, D., Fei, S., Hou, Z., Zhang, H., Sun, C. (eds.) ISNN 2007. LNCS, vol. 4493, pp. 731–740. Springer, Heidelberg (2007)
Beer, R.D.: The Dynamics of Active Categorical Perception in an Evolved Model Agent. Adapt. Behav. 11(4), 209–243 (2003)
Pasemann, F.: Dynamics of a Single Model Neuron. Int. J. Bifurcat. Chaos 3(2), 271–278 (1993)
Manoonpong, P.: Neural Preprocessing and Control of Reactive Walking Machines: Towards Versatile Artificial Perception-Action Systems. In: Cognitive Technologies, Springer, Heidelberg (2007)
Kolodziejski, C., Porr, B., Wörgötter, F.: Mathematical Properties of Neuronal TD-Rules and Differential Hebbian Learning: A Comparison. Biol. Cybern. 98(3), 259–272 (2008)
Oppenheim, A.V., Schafer, R.W., Buck, J.R.: Discrete-time Signal Processing. Prentice-Hall, Englewood Cliffs (1999)
Haykin, S.: Neural Networks Expand SP’s Horizons. IEEE Signal Processing Magazine, 24–49 (1996)
Hanna, A.I., Mandic, D.P., Razaz, M.: A Normalised Backpropagation Learning Algorithm for Multilayer Feed-Forward Neural Adaptive Filters. In: The 2001 IEEE Workshop on Neural Networks for Signal Processing, pp. 63–72 (2001)
Uncini, A.: Audio Signal Processing by Neural Networks. Neurocomputing 55(3-4), 593–625 (2003)
Mandic, D., Chambers, J.: Recurrent Neural Networks for Prediction: Learning Algorithms, Architectures and Stability. Wiley, Chichester (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Manoonpong, P., Pasemann, F., Kolodziejski, C., Wörgötter, F. (2010). Designing Simple Nonlinear Filters Using Hysteresis of Single Recurrent Neurons for Acoustic Signal Recognition in Robots. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds) Artificial Neural Networks – ICANN 2010. ICANN 2010. Lecture Notes in Computer Science, vol 6352. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15819-3_50
Download citation
DOI: https://doi.org/10.1007/978-3-642-15819-3_50
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15818-6
Online ISBN: 978-3-642-15819-3
eBook Packages: Computer ScienceComputer Science (R0)