We briefly review the basic concepts underpinning the ad-aptive 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 in-troduce 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 struc-tured domain to be treated by a neural network or Bayesian approach. The advantage of the proposed approach is the systematicity in the spe-cification 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).
CITATION STYLE
Frasconi, P., Gori, M., & Sperduti, A. (2000). Integration of graphical rules with adaptive learning of structured information. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 1778, pp. 211–225). Springer Verlag. https://doi.org/10.1007/10719871_15
Mendeley helps you to discover research relevant for your work.