Publikation: Towards interpretable quantum machine learning via single-photon quantum walks
Dateien
Datum
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
DOI (zitierfähiger Link)
Internationale Patentnummer
Link zur Lizenz
Angaben zur Forschungsförderung
Austrian Science Fund (FWF): 10.55776/F71
Projekt
Open Access-Veröffentlichung
Sammlungen
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Publikationsstatus
Erschienen in
Zusammenfassung
Variational quantum algorithms represent a promising approach to quantum machine learning where classical neural networks are replaced by parametrized quantum circuits. However, both approaches suffer from a clear limitation, that is a lack of interpretability. Here, we present a variational method to quantize projective simulation (PS), a reinforcement learning model aimed at interpretable artificial intelligence. Decision making in PS is modeled as a random walk on a graph describing the agent's memory. To implement the quantized model, we consider quantum walks of single photons in a lattice of tunable Mach–Zehnder interferometers trained via variational algorithms. Using an example from transfer learning, we show that the quantized PS model can exploit quantum interference to acquire capabilities beyond those of its classical counterpart. Finally, we discuss the role of quantum interference for training and tracing the decision making process, paving the way for realizations of interpretable quantum learning agents.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
Schlagwörter
Konferenz
Rezension
Zitieren
ISO 690
FLAMINI, Fulvio, Marius KRUMM, Lukas J. FIDERER, Thomas MÜLLER, Hans J. BRIEGEL, 2024. Towards interpretable quantum machine learning via single-photon quantum walks. In: Quantum Science and Technology. IOP Publishing. 2024, 9(4), 045011. eISSN 2058-9565. Verfügbar unter: doi: 10.1088/2058-9565/ad5907BibTex
@article{Flamini2024Towar-70527, year={2024}, doi={10.1088/2058-9565/ad5907}, title={Towards interpretable quantum machine learning via single-photon quantum walks}, number={4}, volume={9}, journal={Quantum Science and Technology}, author={Flamini, Fulvio and Krumm, Marius and Fiderer, Lukas J. and Müller, Thomas and Briegel, Hans J.}, note={Article Number: 045011} }
RDF
<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/server/rdf/resource/123456789/70527"> <dc:contributor>Briegel, Hans J.</dc:contributor> <dc:creator>Müller, Thomas</dc:creator> <dc:contributor>Müller, Thomas</dc:contributor> <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/70527/1/Flamini_2-1x5gvqjkf5bek3.pdf"/> <dcterms:title>Towards interpretable quantum machine learning via single-photon quantum walks</dcterms:title> <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by/4.0/"/> <dc:contributor>Krumm, Marius</dc:contributor> <dc:creator>Fiderer, Lukas J.</dc:creator> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/40"/> <dc:contributor>Flamini, Fulvio</dc:contributor> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dc:creator>Flamini, Fulvio</dc:creator> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-08-02T08:27:28Z</dc:date> <dcterms:issued>2024</dcterms:issued> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/40"/> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-08-02T08:27:28Z</dcterms:available> <dc:language>eng</dc:language> <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/70527/1/Flamini_2-1x5gvqjkf5bek3.pdf"/> <dc:creator>Krumm, Marius</dc:creator> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dc:rights>Attribution 4.0 International</dc:rights> <dc:creator>Briegel, Hans J.</dc:creator> <dcterms:abstract>Variational quantum algorithms represent a promising approach to quantum machine learning where classical neural networks are replaced by parametrized quantum circuits. However, both approaches suffer from a clear limitation, that is a lack of interpretability. Here, we present a variational method to quantize projective simulation (PS), a reinforcement learning model aimed at interpretable artificial intelligence. Decision making in PS is modeled as a random walk on a graph describing the agent's memory. To implement the quantized model, we consider quantum walks of single photons in a lattice of tunable Mach–Zehnder interferometers trained via variational algorithms. Using an example from transfer learning, we show that the quantized PS model can exploit quantum interference to acquire capabilities beyond those of its classical counterpart. Finally, we discuss the role of quantum interference for training and tracing the decision making process, paving the way for realizations of interpretable quantum learning agents.</dcterms:abstract> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/70527"/> <dc:contributor>Fiderer, Lukas J.</dc:contributor> </rdf:Description> </rdf:RDF>