This paper concerns learning tasks that require the prediction of a continuous value rather than a discrete class. A general method is presented that allows predictions to use both instance-based and model-based learning. Results with three approaches to constructing models and with eight datasets demonstrate improvements due to the composite method.

1 Knowledge Engineering & Machine Learning Group, Technical University of Catalonia, Barcelona, email: {hnunez, miquel}@lsi.upc.es Abstract. The major hypothesis that we will be prove in this paper is that unsupervised learning techniques of feature weighting are not significantly worse than supervised methods, as is commonly believed in the machine learning community. This paper tests the powe...

We introduce a graphical framework for multiple instance learning (MIL) based on Markov networks. This framework can be used to model the traditional MIL definition as well as more general MIL definitions. Different levels of ambiguity – the portion of positive instances in a bag – can be explored in weakly supervised data. To train these models, we propose a discriminative maxmargin learning a...

Automatic screening of Age-related Macular Degeneration (AMD) is important for both patients and ophthalmologists. The major sign of contracting AMD at the early stage is the appearance of drusen, which are the accumulation of extracellular material and appear as yellow-white spots on the retina. In this paper, we propose an effective approach for drusen segmentation towards AMD screening. The ...