Application of Generalized Dynamic Neural Networks to Biomedical Data

• Published in: IEEE transactions on biomedical engineering Vol. 53; no. 11; pp. 2289 - 2299
• Main Authors: Leistritz, L., Galicki, M., Kochs, E., Zwick, E.B., Fitzek, C., Reichenbach, J.R., Witte, H.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.11.2006; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Bioinformatics; Biomedical Engineering - methods; Classification of temporal sequences; Databases, Factual; Diagnosis, Computer-Assisted - methods; Documentation; dynamic neural networks (DNNs); Information Storage and Retrieval - methods; Medical diagnostic imaging; Neural networks; Neural Networks (Computer); optimal control; Orthopedic surgery; Pattern recognition; Pattern Recognition, Automated - methods; Radiology; Recurrent neural networks; Signal processing algorithms; Signal Processing, Computer-Assisted; Statistics
• ISSN: 0018-9294; 1558-2531
• DOI: 10.1109/TBME.2006.881766

This paper reviews the application of continuous recurrent neural networks with time-varying weights to pattern recognition tasks in medicine. A general learning algorithm based on Pontryagin's maximum principle is recapitulated, and possibilities of improving the generalization capabilities of these networks are given. The effectiveness of the methods is demonstrated by three different real-world examples taken from the fields of anesthesiology, orthopedics, and radiology