Davis Rumelhart and James McClelland have presented a style of neural network modelling called connectionism. They argued that generic associationist networks, subjected to massive amounts of training, could explain all of cognition.

When asked why people were smarter than rats they responded "....People have much more cortex than rats do or even than other primates do; in particular thay have very much more...brain structure not dedicated to input/output - and presumably, this extra cortex is strategically placed in the brain to subserve just those functions that differentiaite people from rats or even apes.... But there must be another aspect to the difference between rats and people as well. This is that the human environment includes other people and the cultural devices that they have developed to organize their thinking processes."

Cultural devices?

Language, for example. Mathematics, too, but that's also a kind of language. So is law. CAD models help us think too.

Colours, as well.

Colors help us think?

Si.

Or is it 'see'?

Subconsciously?

Connectionism is a movement in cognitive science which hopes to explain human intellectual abilities using artificial neural networks (also known as ‘neural networks’ or ‘neural nets’). Neural networks are simplified models of the brain composed of large numbers of units (the analogs of neurons) together with weights that measure the strength of connections between the units. These weights model the effects of the synapses that link one neuron to another. Experiments on models of this kind have demonstrated an ability to learn such skills as face recognition, reading, and the detection of simple grammatical structure.

Philosophers have become interested in connectionism because it promises to provide an alternative to the classical theory of the mind: the widely held view that the mind is something akin to a digital computer processing a symbolic language. Exactly how and to what extent the connectionist paradigm constitutes a challenge to classicism has been a matter of hot debate in recent years.

The word 'culture' was used to refer to the totality of socially transmitted behaviour patterns, arts, beliefs, institutions, and all other products of human work and thought.

It is only a century old.

Franz Boas (1858 - 1942), the father of modern anthropology, embraced George Berkely's theory of idealism and proposed that the differences among human 'races' (cultures) and ethnic groups come not from their physical constitution but from their culture, a system of ideas and values spread by language and other forms of social behaviour. People differ because their cultures differ.

Emile Durkheim (1858 - 1917) - Every time that a social phenomenon is directly explained by a psychological phenomenon, we may be sure that the explanation is false...The group thinks, feels, and acts quite differently from the way in which individual members would were they isolated...If we begin with the individual in seeking to explain phenomena, we shall be able to understand nothing of what takes place in the group...Individual natures are merely the indeterminate material that the social factor molds and transforms. Their contribution consists exclusively in very general attitudes, in vague and consequently plastic predispositions.

The determining cause of a social fact should be sought among the social facts preceding it and not among the states of individual consciousness.

Connectionists have made significant progress in demonstrating the power of neural networks to master cognitive tasks. Here are three well-known experiments that have encouraged connectionists to believe that neural networks are good models of human intelligence. One of the most attractive of these efforts is Sejnowski and Rosenberg's (1987) work on a net that can read English text called NETtalk. The training set for NETtalk was a large data base consisting of English text coupled with its corresponding phonetic output, written in a code suitable for use with a speech synthesizer. Tapes of NETtalk's performance at different stages of its training are very interesting listening. At first the output is random noise. Later, the net sounds like it is babbling, and later still as though it is speaking English double-talk (speech that is formed of sounds that resemble English words). At the end of training, NETtalk does a fairly good job of pronouncing the text given to it. Furthermore, this ability generalizes fairly well to text that was not presented in the training set.
Another influential early connectionist model was a net trained by Rumelhart and McClelland (1986) to predict the past tense of English verbs. The task is interesting because although most of the verbs in English (the regular verbs) form the past tense by adding the suffix ‘-ed’, many of the most frequently verbs are irregular (‘is’ / ‘was’, ‘come’ / ‘came’, ‘go’ / ‘went’). The net was first trained on a set containing a large number of irregular verbs, and later on a set of 460 verbs containing mostly regulars. The net learned the past tenses of the 460 verbs in about 200 rounds of training, and it generalized fairly well to verbs not in the training set. It even showed a good appreciation of "regularities" to be found among the irregular verbs (‘send’ / ‘sent’, ‘build’ / ‘built’; ‘blow’ / ‘blew’, ‘fly’ / ‘flew’). During learning, as the system was exposed to the training set containing more regular verbs, it had a tendency to overregularize, i.e. to combine both irregular and regular forms: (‘break’ / ‘broked’, instead of ‘break’ / ‘broke’). This was corrected with more training. It is interesting to note that children are known to exhibit the same tendency to overregularize during language learning. However, there is hot debate over whether Rumelhart and McClelland's is a good model of how humans actually learn and process verb endings. For example, (Pinker & Prince 1988) point out that the model does a poor job of generalizing to some novel regular verbs. They believe that this is a sign of a basic failing in connectionist models. Nets may be good at making associations and matching patterns, but they have fundamental limitations in mastering general rules such as the formation of the regular past tense. These complaints raise an important issue for connectionist modelers, namely whether nets can generalize properly to master cognitive tasks involving rules. Despite Pinker and Prince's objections, many connectionists believe that generalization of the right kind is still possible (Niklasson and van Gelder, 1994).

Elman's (1991) work on nets that can appreciate grammatical structure has important implications for the debate about whether neural networks can learn to master rules. Elman trained a simple recurrent network to predict the next word in a large corpus of English sentences. The sentences were formed from a simple vocabulary of 23 words using a subset of English grammar. The grammar, though simple, posed a hard test for linguistic awareness. It allowed unlimited formation of relative clauses while demanding agreement between the head noun and the verb. So for example, in the sentence

Any man that chases dogs that chase cats … runs.
the singular ‘man’ must agree with the verb ‘runs’ despite the intervening plural nouns (‘dogs’, ‘cats’) which might cause the selection of ‘run’. One of the important features of Elman's model is the use of recurrent connections. The values at the hidden units are saved in a set of so called context units, to be sent back to the input level for the next round of processing. This looping back from hidden to input layers provides the net with a rudimentary form of memory of the sequence of words in the input sentence. Elman's nets displayed an appreciation of the grammatical structure of sentences that were not in the training set. The net's command of syntax was measured in the following way. Predicting the next word in an English sentence is, of course, and impossible task. However, these nets succeeded, at least by the following measure. At a given point in an input sentence, the output units for words that are grammatical continuations of the sentence at that point should be active and output units for all other words should be inactive. After intensive training, Elman was able to produce nets that displayed perfect performance on this measure including sentences not in the training set. Although this performance is impressive, there is still a long way to go in training nets that can process language. Furthermore, doubts have been raised about the significance of Elman's results. For example, Marcus (1998, 2001) argues that Elman's nets are not able to generalize this performance to sentences formed from a novel vocabulary. This, he claims, is a sign that connectionist models merely associate instances, and are unable to truly master abstract rules.

speaking of David Rumelhart and James McClelland, i would recommend "Parallel Distributed Processing", in 2 vols, published in '86.