4.5 Globalist versus Localist Representations 79
properties could be manifested by AI systems. Rigorously studying the corpus of existing (or hypothetical!) cognitive architectures using these ideas would be a large task, which we do not undertake here.
In the next sections we review several hybrid architectures in more detail, focusing most deeply on LIDA and MicroPsi which have been directly inspirational for CogPrime.
4.5.1 CLARION
Ron Sun’s CLARION architecture (see Figure 4.9) is interesting in its combination of symbolic and neural aspects — a combination that is used in a sophisticated way to embody the distinction and interaction between implicit and explicit mental processes. From a CLARION perspective, architectures like Soar and ACT-R are severely limited in that they deal only with explicit knowledge and associated learning processes.
CLARION consists of a number of distinct subsystems, each of which contains a dual rep- resentational structure, including a “rules and chunks” symbolic knowledge store somewhat similar to ACT-R, and a neural net knowledge store embodying implicit knowledge. The main subsystems are:
e An action-centered subsystem to control actions;
e A non-action-centered subsystem to maintain general knowledge;
e A motivational subsystem to provide underlying motivations for perception, action, and cognition;
e A meta-cognitive subsystem to monitor, direct, and modify the operations of all the other subsystems.
Top Level
action-centered explicit representation
action-centered-implicit non- action-centered representsation implicit representation
non-action-centered |
=| explicit representation
oe
|
| |
( | Bottom Level
Fig. 4.9: The CLARION cognitive architecture.
HOUSE_OVERSIGHT_012995