Concept development in a scaffolded neural network

The scaffolded network is a network of neural networks whose objective is to test the hypothesis that such a compound network can learn increasingly complex concepts in a developmental, cumulative progression. The scaffolded network, which is motivated by physiological and psychological, models, incorporates three kinds of basic neural network architectures: a recurrent cascade network, a Kohonen network, and a recurrent back-propagation network. It is tested by teaching it simple mathematical concepts and functions and then comparing output and intermediate results with data from developmental psychology. This design attempts to extend neural network capabilities to a more robust approximation of cumulative, complex concept learning that occurs during development