Context-dependent neural nets-structures and learning

• Published in: IEEE transaction on neural networks and learning systems 2004-11, Vol.15 (6), p.1367-1377
• Main Authors: Ciskowski, P., Rafajlowicz, E.
• Format: Article
• Language: English
• Subjects: Algorithms; Animals; Artificial Intelligence; Biological neural networks; Classification; Computer Simulation; Context modeling; Contextual modeling; Control systems; Control theory; Decision Support Techniques; Environmental factors; Feedback; Feedforward; Learning; Logistic Models; Machine learning; Models, Biological; Multi-layer neural network; Multilayers; neural network architecture; neural network learning; Neural networks; Neural Networks (Computer); Neurons; Pattern recognition; Pattern Recognition, Automated - methods; Virtual colonoscopy
• ISSN: 1045-9227; 2162-237X; 1941-0093; 2162-2388
• DOI: 10.1109/TNN.2004.837839

A novel approach toward neural networks modeling is presented in the paper. It is unique in the fact that allows nets' weights to change according to changes of some environmental factors even after completing the learning process. The models of context-dependent (cd) neuron, one- and multilayer feedforward net are presented, with basic learning algorithms and examples of functioning. The Vapnik-Chervonenkis (VC) dimension of a cd neuron is derived, as well as VC dimension of multilayer feedforward nets. Cd nets' properties are discussed and compared with the properties of traditional nets. Possibilities of applications to classification and control problems are also outlined and an example presented.