Abstract—The choice value and the testing process against the vigilance parameter ρ, characteristic of ART Neural Network, are merged. Only, a single unique test is required to determine if a committed category node can represent the current input or not. Advantages of APT over ART are: 1-Avoid testing every committed category node before deciding to train a committed category node or a new node must be committed, 2-The vigilance parameter ρ is fixed during training, and 3-The choice value parameter α is eliminated.

Index Terms—Adaptive pointing theory, APT ANN, adaptive resonance theory, ART ANN, ARTMAP, compact fuzzy ART, artificial neural networks.

Kamal R. Al-Rawi is with Department of Computer Science, Faculty of Information Technology, University of Petra, Jordan (e-mail: kamalr@uop.edu.jo).
Consuelo Gonzalo is with Universidad Politécnica de Madrid, Center for Biomedical Technology (CTB), Pozuelo de Alarcón, Spain.

Cite:Kamal R. Al-Rawi and Consuelo Gonzalo, "Adaptive Pointing Theory (APT) Artificial Neural Network," International Journal of Computer and Communication Engineering vol. 3, no. 3, pp. 212-215, 2014.