"A neural network consists of large numbers of simple neurons that are richly interconnected. The weights associated with the connections between neurons determine the characteristics of the network. During a training period, the network adjusts the values of the interconnecting weights. The value of any specific weight has no significance; it is the patterns of weight values in the whole system that bear information. Since these patterns are complex, and are generated by the network itself (by means of a general learning strategy applicable to the whole network), there is no abstract procedure available to describe the process used by the network to solve the problem. There are only complex patterns of relationships."
"Each element in the system is ignorant of the behavior of the system as a whole, it responds only to information that is available to it locally. This point is vitally important. If each element ‘knew’ what was happening to the system as a whole, all of the complexity would have to be present in that element." (Paul Cilliers, "Complexity and Postmodernism: Understanding Complex Systems" , 1998)
"Complex systems operate under conditions far from equilibrium. Complex systems need a constant flow of energy to change, evolve and survive as complex entities. Equilibrium, symmetry and complete stability mean death. Just as the flow, of energy is necessary to fight entropy and maintain the complex structure of the system, society can only survive as a process. It is defined not by its origins or its goals, but by what it is doing." (Paul Cilliers,"Complexity and Postmodernism: Understanding Complex Systems", 1998)
"From a more general philosophical perspective we can say
that we wish to model complex systems because we want to understand them
better. The main requirement for our
models accordingly shifts from having to be correct to being rich in
information. This does not mean that the
relationship between the model and the system itself becomes less important,
but the shift from control and prediction to understanding does have an effect
on our approach to complexity: the evaluation of our models in terms of performance
can be deferred. Once we have a better understanding of the dynamics of
complexity, we can start looking for the similarities and differences between
different complex systems and thereby develop a clearer understanding of the
strengths and limitations of different models."
"Meaning is conferred not by a one-to-one correspondence of a symbol with some external concept or object, but by the relationships between the structural components of the system itself."
"Modelling techniques on powerful computers allow us to
simulate the behaviour of complex systems without having to understand
them. We can do with technology what we
cannot do with science. […] The rise of
powerful technology is not an unconditional blessing. We have
to deal with what we do not understand, and that demands new ways of thinking."
"The ability of neural networks to operate successfully on inputs that did not form part of the training set is one of their most important characteristics. Networks are capable of finding common elements in all the training examples belonging to the same class, and will then respond appropriately when these elements are encountered again. Optimising this capability is an important consideration when designing a network."
"The concept ‘complexity’ is not univocal either. Firstly, it is useful to distinguish between the notions ‘complex’ and ‘complicated’. If a system- despite the fact that it may consist of a huge number of components - can be given a complete description in terms of its individual constituents, such a system is merely complicated. […] In a complex system, on the other hand, the interaction among constituents of the system, and the interaction between the system and its environment, are of such a nature that the system as a whole cannot be fully understood simply by analysing its components. Moreover, these relationships are not fixed, but shift and change, often as a result of self-organisation. This can result in novel features, usually referred to in terms of emergent properties."
"There is no over-arching theory of complexity that allows us to ignore the contingent aspects of complex systems. If something really is complex, it cannot by adequately described by means of a simple theory. Engaging with complexity entails engaging with specific complex systems. Despite this we can, at a very basic level, make general remarks concerning the conditions for complex behaviour and the dynamics of complex systems. Furthermore, I suggest that complex systems can be modelled." (Paul Cilliers," Complexity and Postmodernism", 1998)
No comments:
Post a Comment