74 4 Brief Survey of Cognitive Architectures “T grant the need for non-symbolic processes in some intelligent systems, but I think they sup- plement rather than replace symbol systems. I know of no examples of reasoning, understanding language, or generating complex plans that are best understood as being performed by systems using exclusively non-symbolic processes.... Al systems that achieve human-level intelligence will involve a combination of symbolic and non-symbolic processing.” A few of the more important hybrid cognitive architectures are: e CLARION [SZ04] is a hybrid architecture that combines a symbolic component for reason- ing on “explicit knowledge” with a connectionist component for managing “implicit knowl- edge.” Learning of implicit knowledge may be done via neural net, reinforcement learning, or other methods. The integration of symbolic and subsymbolic methods is powerful, but a great deal is still missing such as episodic knowledge and learning and creativity. Learning in the symbolic and subsymbolic portions is carried out separately rather than dynamically coupled, minimizing “cognitive synergy” effects. e DUAL [NK04] is the most impressive system to come out of Marvin Minsky’s “Society of Mind” paradigm. It features a population of agents, each of which combines symbolic and connectionist representation, selforganizing to collectively carry out tasks such as percep- tion, analogy and associative memory. The approach seems innovative and promising, but it is unclear how the approach will scale to high-dimensional data or complex reasoning problems due to the lack of a more structured high-level cognitive architecture. e LIDA [BF09] is a comprehensive cognitive architecture heavily based on Bernard Baars’ “Global Workspace Theory”. It articulates a “cognitive cycle” integrating various forms of memory and intelligent processing in a single processing loop. The architecture ties in well with both neuroscience and cognitive psychology, but