Title :
A two-processing element adaptable linear oscillating recurrent system with single-weight plasticity
Author :
Johnson, Michael R. ; Principe, Jose C.
Author_Institution :
Florida Univ., Gainesville, FL, USA
Abstract :
A simple recursive linear two-processing element adaptable oscillator is developed and demonstrated. Simple harmonic motion and its mathematical description is the foundation of this study. State equations for an undamped spring-mass system are converted to a discrete time system, followed by eigenvalue analysis to convert the four-degree-of-freedom system to a recursive network with plasticity in one variable. The oscillator is initialized to a frequency in the neighborhood of the desired frequency, and tuned by using resilient backpropagation modified for backpropagation through time. It is shown that the network can track frequencies in a spectrum of operation as defined by the sampling frequency, given the network is initialized to frequencies in the neighborhood of those of interest.
Keywords :
adaptive systems; backpropagation; discrete time systems; eigenvalues and eigenfunctions; linear systems; oscillators; recurrent neural nets; adaptable linear system; discrete time system; eigenvalue analysis; oscillation; recurrent system; recursive oscillator; resilient backpropagation; single-weight plasticity; two-processing element system; Backpropagation; Circuits; Difference equations; Differential equations; Discrete time systems; Eigenvalues and eigenfunctions; Frequency; Inhibitors; Oscillators; Sampling methods;
Conference_Titel :
Neural Networks, 2003. Proceedings of the International Joint Conference on
Print_ISBN :
0-7803-7898-9
DOI :
10.1109/IJCNN.2003.1223286