I also understood that cognitivism had been challenged by connectionists, neuroscientists, behavioural AI researchers (Rodney Brooks), some philosophers (the Churchlands) and some educational theorists (George Siemens, Stephen Downes) who reject the basic premise, ie. they argue that the mind is NOT like a computer ❋ Bill Kerr (2008)
(Another way of putting this is to say that for classicists mental representations are computationally atomic, whereas for connectionists they are not.) ❋ Pitt, David (2008)
Also the idea of mental representation cognitive stuctures is attacked by the connectionists who think it can all be done with patterns - Downes also argues this ❋ Bill Kerr (2008)
Moreover, connectionists argue that information processing as it occurs in connectionist networks more closely resembles some features of actual human cognitive functioning. ❋ Pitt, David (2008)
The major points of controversy in the philosophical literature on connectionism have to do with whether connectionists provide a viable and novel paradigm for understanding the mind. ❋ Garson, James (2007)
But such tasks as language and reasoning cannot be accomplished by associative methods alone and so connectionists are unlikely to match the performance of classical models at explaining these higher-level cognitive abilities. ❋ Garson, James (2007)
So the only tactic for securing a telling objection to connectionists along these lines would be to weaken the requirement on the explanation of systematicity to one which classical architectures can and connectionists cannot meet. ❋ Garson, James (2007)
However many connectionists do not view their work as a challenge to classicism and some overtly support the classical picture. ❋ Garson, James (2007)
So radical connectionists would eliminate symbolic processing from cognitive science forever. ❋ Garson, James (2007)
Implementational connectionism may succeed, but radical connectionists will never be able to account for the mind. ❋ Garson, James (2007)
Despite Pinker and Prince's objections, many connectionists believe that generalization of the right kind is still possible (Niklasson and van Gelder 1994). ❋ Garson, James (2007)
Although classical systems are capable of multiple constraint satisfaction, connectionists argue that neural network models provide much more natural mechanisms for dealing with such problems. ❋ Garson, James (2007)
So if connectionists can establish that brain processing is essentially non-symbolic, eliminativist conclusions will follow. ❋ Garson, James (2007)
However, most connectionists who promote similarity based accounts of meaning reject many of the presupposition of standard theories. ❋ Garson, James (2007)
Calvo Garzon (2003) complains that there are reasons to think that connectionists must fail. ❋ Garson, James (2007)
Here are three well-known experiments that have encouraged connectionists to believe that neural networks are good models of human intelligence. ❋ Garson, James (2007)
So-called implementational connectionists seek an accommodation between the two paradigms. ❋ Garson, James (2007)
However, many connectionists resist the implementational point of view. ❋ Garson, James (2007)
