Every indexed document

the spread of activation through the network is designed to

which has some significant similarities to CogPrime. Similar to our current research

scalable cognitive synergy. It would likely be possible

and they form coalitions which collectively represent

manipulated using formal rules. The agents exchange messages and activation via

in his PhD thesis and followup work [SBC05]

he is also not so effective at relating these emotional

“Minsky does a marvelous job parsing other complicated mental activities

famously arguing: “What magical trick makes us intelligent? The trick

each of which contains a dual representational

it is also reasonable to conjecture that this

interaction may be asymmetric: one component may

the neural and symbolic components don’t exchange

and what we are referring to is the frequency of high-informationcontent

because the main interest of their review is in monolithic systems. We

but playing a clearly derived and secondary role. We prefer

language and usage. “Language” refers to the type of language used in the symbolic

a paper that gives an elegant categorization of neural-symbolic AI systems. Figure

or using logical or neural net components

and globalist versus localist knowledge representation.