1. Neural network methods for one-to-many multi-valued mapping problems
- Author
-
Jayne, C., Lanitis, A., Christodoulou, Chris C., and Christodoulou, Chris C. [0000-0001-9398-5256]
- Subjects
Multivariate statistics ,Computer science ,Multivariant analysis ,Single parameter ,Multivariate normal distribution ,computer.software_genre ,Radial basis functions ,Standard neural ,Multivalued mappings ,Single variable ,Mixture distribution ,Radial basis function ,Single source ,Artificial neural network ,Pattern recognition systems ,Multiple parameters ,Complex mapping ,Mapping ,Problem domain ,General index ,Neural networks ,Topographic mapping ,One-to-many mapping ,Stock shares ,Network-based ,Multilayer neural networks ,Neural network method ,Latent variable ,Machine learning ,Humanities ,Artificial Intelligence ,Input parameter ,Exam grades prediction ,Ill-conditioned ,business.industry ,Arts ,Sources of variation ,Pattern recognition ,Latent variable methods ,Stock price prediction ,Perceptron ,Radial basis function networks ,Mixture density ,Multivariate distributions ,Artificial intelligence ,High school ,business ,computer ,Software ,Forecasting - Abstract
An investigation of the applicability of neural network-based methods in predicting the values of multiple parameters, given the value of a single parameter within a particular problem domain is presented. In this context, the input parameter may be an important source of variation that is related with a complex mapping function to the remaining sources of variation within a multivariate distribution. The definition of the relationship between the variables of a multivariate distribution and a single source of variation allows the estimation of the values of multiple variables given the value of the single variable, addressing in that way an ill-conditioned one-to-many mapping problem. As part of our investigation, two problem domains are considered: predicting the values of individual stock shares, given the value of the general index, and predicting the grades received by high school pupils, given the grade for a single course or the average grade. With our work, the performance of standard neural network-based methods and in particular multilayer perceptrons (MLPs), radial basis functions (RBFs), mixture density networks (MDNs) and a latent variable method, the general topographic mapping (GTM), is compared. According to the results, MLPs and RBFs outperform MDNs and the GTM for these one-to-many mapping problems. © 2010 Springer-Verlag London Limited. 20 6 775 785 Cited By :5
- Published
- 2011