Inductive bias strength in knowledge-based neural networks: application to magnetic resonance spectroscopy of breast tissues Christian W. Omlin a,* , Sean Snyders b,1 a Department of Computer Science, University of the Western Cape, 7535 Bellville, South Africa b Department of Computer Science, University of Stellenbosch, 7600 Stellenbosch, South Africa Received 30 April 2001; received in revised form 14 April 2003; accepted 6 May 2003 Abstract The integration of symbolic knowledge with artificial neural networks is becoming an increasingly popular paradigm for solving real-world applications. The paradigm provides means for using prior knowledge to determine the network architecture, to program a subset of weights to induce a learning bias which guide network training, and to extract knowledge from trained networks. The role of neural networks then becomes that of knowledge refinement. It thus provides a methodology for dealing with uncertainty in the prior knowledge. We address the open question of how to determine the strength of the inductive bias of programmed weights; we present a quantitative solution which takes the network architecture, the prior knowledge, and the training data into consideration. We apply our solution to the difficult problem of analyzing breast tissue from magnetic resonance spectroscopy (MRS); the available database is extremely limited and cannot be adequately explained by expert knowledge alone. # 2003 Elsevier B.V. All rights reserved. Keywords: Knowledge-based neural networks; Inductive bias; Learning with hints; Training and generalization performance; 31 P magnetic resonance spectroscopy; Breast tissue 1. Introduction 1.1. Expert knowledge and inductive learning Medical decision making is well-suited for the application of artificial intelligence techniques [23,37]. Expert knowledge about disease processes is available which can be Artificial Intelligence in Medicine 28 (2003) 121–140 * Corresponding author. E-mail addresses: comlin@uwc.ac.za (C.W. Omlin), sean.snyders@i-u.de (S. Snyders). 1 Present address: Computational Intelligence Group, School of Information Technology, International University, 76646 Bruchsal, Germany. 0933-3657/$ – see front matter # 2003 Elsevier B.V. All rights reserved. doi:10.1016/S0933-3657(03)00062-9