Weights optimization for multi-instance multi-label RBF neural networks using steepest descent method

• Published in: Neural computing & applications Vol. 22; no. 7-8; pp. 1563 - 1569
• Main Authors: Li, Cunhe, Shi, Guoqiang
• Format: Journal Article
• Language: English
• Published: London Springer-Verlag 01.06.2013; Springer
• Subjects: Applied sciences; Artificial Intelligence; Calculus of variations and optimal control; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Computer science; control theory; systems; Data Mining and Knowledge Discovery; Exact sciences and technology; Image Processing and Computer Vision; Inference from stochastic processes; time series analysis; Learning and adaptive systems; Mathematical analysis; Mathematics; Numerical analysis; Numerical analysis. Scientific computation; Numerical methods in mathematical programming, optimization and calculus of variations; Numerical methods in optimization and calculus of variations; Original Article; Probability and statistics; Probability and Statistics in Computer Science; Sciences and techniques of general use; Statistics; Radial basis function; Multi-instance multi-label learning; Neural networks; Machine learning; Neural computation; Error estimation; Steepest descent method; Optimization method; Neural network; Learning algorithm; Optimization; Singular value decomposition
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-012-0815-7

Multi-instance multi-label learning (MIML) is an innovative learning framework where each sample is represented by multiple instances and associated with multiple class labels. In several learning situations, the multi-instance multi-label RBF neural networks (MIMLRBF) can exploit connections between the instances and the labels of an MIML example directly, while most of other algorithms cannot learn that directly. However, the singular value decomposition (SVD) method used to compute the weights of the output layer will cause augmented overall error in network performance when training data are noisy or not easily discernible. This paper presents an improved approach to learning algorithms used for training MIMLRBF. The steepest descent (SD) method is used to optimize the weights after they are initialized by the SVD method. Comparing results employing diverse learning strategies shows interesting outcomes as have come out of this paper.