Image classification by integration of neural networks and machine learning

A new approach is proposed for the integration of neural networks (NN) with machine learning techniques to build up an image classification system. In particular, the author uses a symbolic technique for inductive learning from examples to provide object models. Such models are used to design the architecture and to initialize the weights of a backpropagation NN. Models include uncertainty aspects represented by fuzzy predicates, and relational properties for contextual classification. Both aspects are suitably mapped into the automatically designed NN. Preliminary results in a biomedical application are presented