D-FANNS (dynamical functional artificial neural networks)-a new avenue for intelligent analog signal processing

Summary form only given. Intelligent signal processing may be defined as the process of mapping a signal x into a binary vector or matrix y, so that y enables the detection, classification, or interpretation of an event present in x. (In the case of an interpretation in an appropriate language, y would represent a digitally coded relational structure.) We denote by f the input-output map of such an intelligent signal processing filter. In a number of applications, it is possible to naturally implement the nonlinear filter map f by an artificial neural network (ANN). We consider the case in which x is an analog signal (waveform) belonging to L2(I), where I is an appropriate interval of the real line R1 (i.e., L2(I) is the space of square integrable functions on I), and propose the realization of f by an artificial neural network in which the synaptic weight actions of the first layer are implemented by a filter bank. We call such a network a dynamical functional artificial neural network (D-FANN) to distinguish it from a conventional functional artificial neural network (FANN), where a synaptic weight action is implemented by a scalar product (integration) in L2(I), between the incoming waveform x and a “distributed” functional weight. Compared with conventional FANNs, D-FANNs permit simple and meaningful causal realizations of intelligent analog signal processors. A novel element in the present paper is the introduction of a “D-FANN gain equation”, in a way analogous to that in Kalman filtering. Applications of D-FANNs to real and simulated data are now in progress and these results are discussed