Integration of Graphical-Based Rules with Adaptive Learning of Structured Information

We briefly review the basic concepts underpinning the adaptive processing of data structures as outlined in [3]. Then, turning to practical applications of this framework, we argue that stationarity of the computational model is not always desirable. For this reason we introduce very briefly our idea on how a priori knowledge on the domain can be expressed in a graphical form, allowing the formal specification of perhaps very complex (i.e., non-stationary) requirements for the structured domain to be treated by a neural network or Bayesian approach. The advantage of the proposed approach is the systematicity in the specification of both the topology and learning propagation of the adopted computational model (i.e., either neural or probabilistic, or even hybrid by combining both of them).