• search hit 1 of 1
Back to Result List

Prediction of neural network performance by phenotypic modeling

  • Surrogate models are used to reduce the burden of expensive-to-evaluate objective functions in optimization. By creating models which map genomes to objective values, these models can estimate the performance of unknown inputs, and so be used in place of expensive objective functions. Evolutionary techniques such as genetic programming or neuroevolution commonly alter the structure of the genome itself. A lack of consistency in the genotype is a fatal blow to data-driven modeling techniques: interpolation between points is impossible without a common input space. However, while the dimensionality of genotypes may differ across individuals, in many domains, such as controllers or classifiers, the dimensionality of the input and output remains constant. In this work we leverage this insight to embed differing neural networks into the same input space. To judge the difference between the behavior of two neural networks, we give them both the same input sequence, and examine the difference in output. This difference, the phenotypic distance, can then be used to situate these networks into a common input space, allowing us to produce surrogate models which can predict the performance of neural networks regardless of topology. In a robotic navigation task, we show that models trained using this phenotypic embedding perform as well or better as those trained on the weight values of a fixed topology neural network. We establish such phenotypic surrogate models as a promising and flexible approach which enables surrogate modeling even for representations that undergo structural changes.

Export metadata

Additional Services

Share in Twitter Search Google Scholar Availability
Metadaten
Document Type:Conference Object
Language:English
Author:Alexander Hagg, Martin Zaefferer, Jörg Stork, Adam Gaier
Parent Title (English):GECCO '19: Genetic and Evolutionary Computation Conference, Prague, Czech Republic, July 13-17, 2019
First Page:1576
Last Page:1582
ISBN:978-1-4503-6748-6
DOI:https://doi.org/10.1145/3319619.3326815
ArXiv Id:http://arxiv.org/abs/1907.07075
Publisher:ACM
Place of publication:New York, NY, USA
Date of first publication:2019/07/13
Departments, institutes and facilities:Fachbereich Informatik
Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE)
Dewey Decimal Classification (DDC):0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Entry in this database:2019/07/13