Dynamic backpropagation algorithm for neural network controlled resonator-bank architecture

An adaptive processing system that consists of a resonator-based digital filter and a neural network is presented. The filter section realizes the dynamics of the adaptive system, while the transfer characteristics are controlled by the neural network. The author focuses on online training algorithms that can create an association between features of the input signal of the neural network and dynamic responses of the digital filter. A dynamic back propagation algorithm is derived for training the network in closed-loop configurations, when a feedback path exists between the output of the digital filter section and inputs to the neural network. Simulation results show that the neural network controlled resonator-bank architecture is computationally feasible and can be used as a general building block in a wide range of identification and control problems