The abilities of neural networks to abstract and to use abstractions

摘要

The representation of concrete objects in neural networks is one of the important research areas in cognitive modeling. In the present work, the problem of the degree of abstractness is briefly considered, and some central concepts involving the representation of abstract entities are discussed. The epistemological status of the ability to use abstractions is discussed, and a proposal concerning the use of 'functants' in modeling abstract entities is considered.