Learning with Differentiable Algorithms

Cite This

Files in this item

Checksum: MD5:b0ec9c58ffe4c1d2770191c9209ba890

PETERSEN, Felix, 2022. Learning with Differentiable Algorithms [Dissertation]. Konstanz: University of Konstanz

@phdthesis{Petersen2022Learn-58475, title={Learning with Differentiable Algorithms}, year={2022}, author={Petersen, Felix}, address={Konstanz}, school={Universität Konstanz} }

<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:bibo="http://purl.org/ontology/bibo/" xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:void="http://rdfs.org/ns/void#" xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > <rdf:Description rdf:about="https://kops.uni-konstanz.de/rdf/resource/123456789/58475"> <dc:creator>Petersen, Felix</dc:creator> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/> <dc:rights>terms-of-use</dc:rights> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dc:language>eng</dc:language> <dc:contributor>Petersen, Felix</dc:contributor> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/58475"/> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dcterms:issued>2022</dcterms:issued> <dcterms:title>Learning with Differentiable Algorithms</dcterms:title> <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/58475/3/Petersen_2-1qlgm6rvkz9m08.pdf"/> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/58475/3/Petersen_2-1qlgm6rvkz9m08.pdf"/> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-09-01T13:18:13Z</dc:date> <dcterms:abstract xml:lang="eng">Classic algorithms and machine learning systems like neural networks are both abundant in everyday life. While classic computer science algorithms are suitable for precise execution of exactly defined tasks such as finding the shortest path in a large graph, neural networks allow learning from data to predict the most likely answer in more complex tasks such as image classification, which cannot be reduced to an exact algorithm. To get the best of both worlds, this thesis explores combining both concepts leading to more robust, better performing, more interpretable, more computationally efficient, and more data efficient architectures. The thesis formalizes the idea of algorithmic supervision, which allows a neural network to learn from or in conjunction with an algorithm. When integrating an algorithm into a neural architecture, it is important that the algorithm is differentiable such that the architecture can be trained end-to-end and gradients can be propagated back through the algorithm in a meaningful way. To make algorithms differentiable, this thesis proposes a general method for continuously relaxing algorithms by perturbing variables and approximating the expectation value in closed form, i.e., without sampling. In addition, this thesis proposes differentiable algorithms, such as differentiable sorting networks, differentiable renderers, and differentiable logic gate networks. Finally, this thesis presents alternative training strategies for learning with algorithms.</dcterms:abstract> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-09-01T13:18:13Z</dcterms:available> </rdf:Description> </rdf:RDF>

Downloads since Sep 1, 2022 (Information about access statistics)

Petersen_2-1qlgm6rvkz9m08.pdf 35

This item appears in the following Collection(s)

Search KOPS


Browse

My Account