68 4 Brief Survey of Cognitive Architectures Hierarchical control system top level node ; ¥ tasks, goals sensations, results ~ node | node | | sensor | | actuator | sensor/actuator r os or rm sensations] actions sensations actions Controlled system, controlled process, or environment | Fig. 4.5: A standard, general-purpose hierarchical control architecture. DeSTIN’s control hi- erarchy exemplifies this architecture, with the difference lying mainly in the DeSTIN control hierarchy’s tight integration with the state inference (perception) and critic (reinforcement) hierarchies. between such units. However, this paradigm has its limitations; for instance, these approaches do not represent temporal information with the same ease as spatial structure. Moreover, some key constraints are imposed on the learning schemes driving these architectures, namely the need for layer-by-layer training, and oftentimes pre-training. DeSTIN overcomes the limitations of prior deep learning approaches to perception processing, and also extends beyond perception to action and reinforcement learning. 4.3.1.2 DeSTIN for Perception Processing The hierarchical architecture of DeSTIN’s spatiotemporal inference network comprises an ar- rangement into multiple layers of “nodes” comprising multiple instantiations of an identical cortical circuit. Each node corresponds to a particular spatiotemporal region, and uses a sta- tistical learning algorithm to characterize the sequences of patterns that are presented to it by nodes in the layer beneath it. More specifically, e At the very lowest layer of the hierarchy nodes receive as input raw data (e.g. pixels of an image) and continuously construct a belief state that attempts to characterize the sequences of patterns viewed. HOUSE_OVERSIGHT_012984