AutoAssociative Pyramidal Neural Network for one class pattern classification with implicit feature extraction

• We propose an autoassociative pyramidal neural network called AAPNet.
• AAPNet extracts features implicitly.
• AAPNet creates closed decision boundaries.
• The emergence of an unknown class does not affect the trained AAPNets.
• When compared with other methods, AAPNet obtains better accuracy rates.

Receptive fields and autoassociative memory are brain concepts that have individually inspired many artificial models, but models using both ideas have not been deeply studied. In this paper, we propose the AutoAssociative Pyramidal Neural Network (AAPNet), which is an artificial neural network for one-class classification that uses autoassociative memory and receptive field concepts in its pyramidal architecture. The proposed neural network performs implicit feature extraction and learns how to reconstruct a pattern from such features. The AAPNet is evaluated using the object categorization Caltech-101 database and presents better results when compared with other state-of-the-art methods.