AutoAssociative Pyramidal Neural Network for one class pattern classification with implicit feature extraction
作者：
Highlights：
• 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.
摘要
•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.
论文关键词：Neural networks,Receptive fields,Autoassociative memory,One-class classification,Computer vision
论文评审过程：Available online 12 July 2013.
论文官网地址：https://doi.org/10.1016/j.eswa.2013.06.080
