Interactive Media Systems, TU Wien

Machine Learning with Dual Process Models

By Horst Eidenberger, Bert Klauninger, and Martin Unger

Abstract

Similarity measurement processes are a core part of most machine learning algorithms. Traditional approaches focus on either taxonomic or thematic thinking. Psychological research suggests that a combination of both is needed to model human-like similarity perception adequately. Such a combination is called a Similarity Dual Process Model (DPM). This paper describes how to construct DPMs as a linear combination of existing measures of similarity and distance. We use generalisation functions to convert distance into similarity. DPMs are similar to kernel functions. Thus, they can be integrated into any machine learning algorithm that uses kernel functions.Clearly, not all DPMs that can be formulated work equally well. Therefore we test classification performance in a real-world task: the detection of pedestrians in images. We assume that DPMs are only viable if they yield better classifiers than their constituting parts. In our experiments, we found DPM kernels that matched the performance of conventional ones for our data set. Eventually, we provide a construction kit to build such kernels to encourage further experiments in other application domains of machine learning.

Reference

H. Eidenberger, B. Klauninger, M. Unger: "Machine Learning with Dual Process Models"; Talk: 5th International Conference on Pattern Recognition Applications and Methods, Rom; 02-24-2016 - 02-26-2016; in: "Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods", (2016), ISBN: 989-758-173-1; 148 - 153.

BibTeX

Click into the text area and press Ctrl+A/Ctrl+C or ⌘+A/⌘+C to copy the BibTeX into your clipboard… or download the BibTeX.