more from this thinker     |     more from this text

Single Idea 4998

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

Full Idea

In a connectionist system, information is represented not by sentences but by the total distribution of connection strengths.

Gist of Idea

Instead of representation by sentences, it can be by a distribution of connectionist strengths

Source

Robert Kirk (Mind and Body [2003], §7.6)

Book Ref

Kirk,Robert: 'Mind and Body' [Acumen 2003], p.149

A Reaction

Neither sentences (of a language of thought) NOR connection strengths strike me as very plausible ways for a brain to represent things. It must be something to do with connections, but it must also be to do with neurons, or we get bizarre counterexamples.

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

3075 Could a cloud have a headache if its particles formed into the right pattern? [Harman]
2490 Modern connectionism is just Hume's theory of the 'association' of 'ideas' [Fodor]
2447 Hume has no theory of the co-ordination of the mind [Fodor]
12624 Only the labels of nodes have semantic content in connectionism, and they play no role [Fodor]
2991 Hume's associationism offers no explanation at all of rational thought [Fodor]
4998 Instead of representation by sentences, it can be by a distribution of connectionist strengths [Kirk,R]
3200 Pattern recognition is puzzling for computation, but makes sense for connectionism [Rey]
3201 Connectionism explains well speed of perception and 'graceful degradation' [Rey]
3202 Connectionism explains irrationality (such as the Gamblers' Fallacy) quite well [Rey]
3199 Connectionism assigns numbers to nodes and branches, and plots the outcomes [Rey]
2984 Perceptions could give us information without symbolic representation [Lyons]
7511 Neural networks can generalise their training, e.g. truths about tigers apply mostly to lions [Pinker]
7512 There are five types of reasoning that seem beyond connectionist systems [Pinker, by PG]
18562 Connectionists cannot distinguish concept-memories from their background, or the processes [Machery]