more from this thinker     |     more from this text


Single Idea 12624

[filed under theme 17. Mind and Body / E. Mind as Physical / 4. Connectionism ]

Full Idea

Connectionism has no truck with mental representations; on the one hand, only the node labels in 'neural networks' have semantic content, and, on the other, the node labels play no role in mental processes, in standard formulations.

Gist of Idea

Only the labels of nodes have semantic content in connectionism, and they play no role

Source

Jerry A. Fodor (LOT 2 [2008], Ch.1)

Book Ref

Fodor,Jerry A.: 'LOT 2: the Language of Thought Revisited' [OUP 2008], p.7


A Reaction

Connectionism must have some truth in it, yet mere connections can't do the full job. The difficulty is that nothing else seems to do the 'full job' either. Fodor cites productivity, systematicity, compositionality, logical form as the problems.


The 14 ideas with the same theme [mind is the sum of many associations/connections]:

Could a cloud have a headache if its particles formed into the right pattern? [Harman]
Modern connectionism is just Hume's theory of the 'association' of 'ideas' [Fodor]
Hume has no theory of the co-ordination of the mind [Fodor]
Only the labels of nodes have semantic content in connectionism, and they play no role [Fodor]
Hume's associationism offers no explanation at all of rational thought [Fodor]
Instead of representation by sentences, it can be by a distribution of connectionist strengths [Kirk,R]
Pattern recognition is puzzling for computation, but makes sense for connectionism [Rey]
Connectionism explains well speed of perception and 'graceful degradation' [Rey]
Connectionism explains irrationality (such as the Gamblers' Fallacy) quite well [Rey]
Connectionism assigns numbers to nodes and branches, and plots the outcomes [Rey]
Perceptions could give us information without symbolic representation [Lyons]
Neural networks can generalise their training, e.g. truths about tigers apply mostly to lions [Pinker]
There are five types of reasoning that seem beyond connectionist systems [Pinker, by PG]
Connectionists cannot distinguish concept-memories from their background, or the processes [Machery]