Multilayer perceptron training with multiobjective memetic optimization
Published inJyväskylä studies in computing
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. ...
PublisherUniversity of Jyväskylä
MetadataShow full item record
- Väitöskirjat 
Showing items with similar title or keywords.
Algorithmic issues in computational intelligence optimization : from design to implementation, from implementation to design Caraffini, Fabio (University of Jyväskylä, 2016)The vertiginous technological growth of the last decades has generated a variety of powerful and complex systems. By embedding within modern hardware devices sophisticated software, they allow the solution of complicated ...
Iacca, Giovanni (University of Jyväskylä, 2011)
Tree species classification of drone hyperspectral and RGB imagery with deep learning convolutional neural networks Nezami, Somayeh; Khoramshahi, Ehsan; Nevalainen, Olli; Pölönen, Ilkka; Honkavaara, Eija (MDPI AG, 2020)Interest in drone solutions in forestry applications is growing. Using drones, datasets can be captured flexibly and at high spatial and temporal resolutions when needed. In forestry applications, fundamental tasks include ...
Zolotukhin, Mikhail (University of Jyväskylä, 2014)
DUNE Collaboration (American Physical Society, 2020)The Deep Underground Neutrino Experiment is a next-generation neutrino oscillation experiment that aims to measure CP-violation in the neutrino sector as part of a wider physics program. A deep learning approach based on ...