2026-09-18T18:11:27Z https://opus4.kobv.de/opus4-uni-passau/oai

oai:kobv.de-opus4-uni-passau:1496 2025-08-13 bibliography:false doc-type:PhDThesis open_access ddc ddc:004 ddc:510

Structure of Artificial Neural Networks : Empirical Investigations 0000-0001-5710-9240 Julian Stier 004 510 neural architecture deep learning graph induced neural networks Within one decade, Deep Learning overtook the dominating solution methods of countless problems of artificial intelligence. "Deep" refers to the deep architectures with operations in manifolds of which there are no immediate observations. For these deep architectures some kind of structure is pre-defined -- but what is this structure? With a formal definition for structures of neural networks, neural architecture search problems and solution methods can be formulated under a common framework. Both practical and theoretical questions arise from closing the gap between applied neural architecture search and learning theory. Does structure make a difference or can it be chosen arbitrarily? This work is concerned with deep structures of artificial neural networks and examines automatic construction methods under empirical principles to shed light on to the so called ``black-box models''. Our contributions include a formulation of graph-induced neural networks that is used to pose optimisation problems for neural architecture. We analyse structural properties for different neural network objectives such as correctness, robustness or energy consumption and discuss how structure affects them. Selected automation methods for neural architecture optimisation problems are discussed and empirically analysed. With the insights gained from formalising graph-induced neural networks, analysing structural properties and comparing the applicability of neural architecture search methods qualitatively and quantitatively we advance these methods in two ways. First, new predictive models are presented for replacing computationally expensive evaluation schemes, and second, new generative models for informed sampling during neural architecture search are analysed and discussed. Universität Passau Passau Innstrasse 29, 94032 Passau Michael Granitzer Mathilde Mougeot 2024-09-26 2024-10-11 PhDThesis Text urn:nbn:de:bvb:739-opus4-14968 application/pdf eng Creative Commons - CC BY-SA - Namensnennung - Weitergabe unter gleichen Bedingungen 4.0 International thesis.doctoral Universität Passau Passau Fakultät für Informatik und Mathematik 1 https://opus4.kobv.de/opus4-uni-passau/oai/container/index/docId/1496 https://opus4.kobv.de/opus4-uni-passau/frontdoor/index/index/docId/1496