University of Jyväskylä

Dissertation: 9.12.2016 Multilayer Perceptron Training with Multiobjective Memetic Optimization (Nieminen)

Start date: Dec 09, 2016 12:00 PM

End date: Dec 09, 2016 03:00 PM

Location: Mattilanniemi, MaA 103

Paavo Nieminen
Paavo Nieminen

M.Sc. Paavo Nieminen defends his doctoral dissertation in Information Technology ”Multilayer Perceptron Training with Multiobjective Memetic Optimization”. Opponent Associate Professor Dr. Carlos Cotta (Universidad de Màlaga) and custos Professor Tommi Kärkkäinen (University of Jyväskylä).

Abstract

Machine learning tasks usually come with several mutually conflicting objectives. One example is the simplicity of the learning device contrasted with the accuracy of its performance after learning. Another common example is the trade-off that must often be made between the rate of false positive and false negative predictions in diagnostic applications. For computer programs that learn from data, these objectives are formulated as mathematical functions, each of which describes one facet of the desired learning outcome. Even functions that intend to optimize the same facet may behave in a subtly different and mutually conflicting way, depending on the task and the dataset being examined. Multiobjective optimization methods developed for simultaneous optimization of such multiple objectives found their way to machine learning a few decades ago.

This dissertation discusses the past and current uses of multiobjective optimization in supervised learning, especially in training a multilayer perceptron (MLP) artificial neural network for object classification. A literature overview of multiobjective MLP training is presented, supported by a semi-automatic survey using a software tool created partly by the author. Based on the literature, key goals and algorithmic elements are identified and applied to create a new framework for training MLPs consistent with an implementation used earlier for industrial projects using single-objective methods. Simulated datasets are used to illustrate the functionality of the created training algorithm, and how memetic Pareto-based multiobjective learning can be used for MLP classifier training. Emphasis is put on formulating useful representations and objective functions for the task.

The dissertation is published in the series Jyväskylä Studies in Computing. ISSN 1456-5390; 247; ISBN 978-951-39-6823-6 (nid.); ISBN 978-951-39-6824-3 (PDF) E-publication: https://jyx.jyu.fi/dspace/handle/123456789/51933

It is available at the Soppi University Shop and University of Jyväskylä Web Store, tel. +358 (0)40 805 3825, myynti@library.jyu.fi

Further information:

Paavo Nieminen, puh. 040 576 8507, paavo.j.nieminen@jyu.fi
Communications Officer Anitta Kananen tiedotus@jyu.fi, puh. +358 40 805 4142