Common to cognitive architecture is the belief that understanding (human) cognitive processing means being able to implement them on a computational level. Cognitive architectures can be characterized by certain properties or goals that are as follows:
Implementation of not just various different aspects of cognitive behavior but of cognition as a whole (Holism, e.g. Unified theory of cognition). This is in contrast to cognitive models.
The architecture often tries to reproduce the behavior of the modelled system (human ...
Cognitive architectures can be symbolic, connectionist, or hybrid. Some cognitive architecures or models base on a set of generic rules, as, e.g., the Information Processing Language (such as e.g. SOAR based on the unified theory of cognition, or similarly ACT). Many of these architectures base on a the-mind-is-like-a-computer analogy. In contrast subsymbolic processing specifies no such rules a priori and relies on emergent properties of processing units (e.g. nodes). A further distinction is whether the architecture is centralized with a n ...
