4.3 Emergentist Cognitive Architectures 69

4.3 Emergentist Cognitive Architectures 69 e The second layer, and all those above it, receive as input the belief states of nodes at their corresponding lower layers, and attempt to construct belief states that capture regularities in their inputs. e Each node also receives as input the belief state of the node above it in the hierarchy (which constitutes “contextual” information) Feedback (contextual) P(s*|S) signals P(O|S") P(Ss"|S.C) P(s"|5,C) P(O|s’) # ™ P(O]S’) P(S"| S.C) P(S']5.C) P(S']5,C) P(S'|S,C) P(O|S*) P(O|S*) P(O!|S*) P(O]S’) Observation (e.g. 32x32 image) Fig. 4.6: Small-scale instantiation of the DeSTIN perceptual hierarchy. Each box represents a node, which corresponds to a spatiotemporal region (nodes higher in the hierarchy corresponding to larger regions). O denotes the current observation in the region, C is the state of the higher- layer node, and S and S’ denote state variables pertaining to two subsequent time steps. In each node, a statistical learning algorithm is used to predict subsequent states based on prior states, current observations, and the state of the higher-layer node. More specifically, each of the DeSTIN nodes, referring to a specific spacetime region, contains a set of state variables conceived as clusters, each corresponding to a set of previously-observed sequences of events. These clusters are characterized by centroids (and are hence assumed roughly spherical in shape), and each of them comprises a certain "spatiotemporal form" recog- nized by the system in that region. Each node then contains the task of predicting the likelihood of a certain centroid being most apropos in the near future, based on the past history of ob- servations in the node. This prediction may be done by simple probability tabulation, or via HOUSE_OVERSIGHT_012985