Many relationships among data in several areas (such as computer vision, molecular chemistry and pattern recognition) can be represented by graphs. In the machine learning setting, it is an important learning task to classify graph-structural data correctly. Typically, the established techniques for this setting proceed via graph kernels and neural-network classification. In this work, we explore end-to-end learning for graphs: the objective is to operate on the graph representations directly. The key idea of our approach is to use standard tools for graph canonization. We test the performance of this approach on several datasets arising from bioinformatics. In general, we find that the graph canonization, as such, does not improve the accuracy of the classification. A possible reason for this behavior is that the neural network ends up overfitting to the given adjacency matrix representation.
Die Inhaltsangabe kann sich auf eine andere Ausgabe dieses Titels beziehen.
Anbieter: Books Puddle, New York, NY, USA
Zustand: New. Bestandsnummer des Verkäufers 26388700745
Anzahl: 4 verfügbar
Anbieter: BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Deutschland
Taschenbuch. Zustand: Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -Many relationships among data in several areas (such as computer vision, molecular chemistry and pattern recognition) can be represented by graphs. In the machine learning setting, it is an important learning task to classify graph-structural data correctly. Typically, the established techniques for this setting proceed via graph kernels and neural-network classification. In this work, we explore end-to-end learning for graphs: the objective is to operate on the graph representations directly. The key idea of our approach is to use standard tools for graph canonization. We test the performance of this approach on several datasets arising from bioinformatics. In general, we find that the graph canonization, as such, does not improve the accuracy of the classification. A possible reason for this behavior is that the neural network ends up overfitting to the given adjacency matrix representation. 52 pp. Englisch. Bestandsnummer des Verkäufers 9786202224178
Anzahl: 2 verfügbar
Anbieter: Majestic Books, Hounslow, Vereinigtes Königreich
Zustand: New. Print on Demand. Bestandsnummer des Verkäufers 391947670
Anzahl: 4 verfügbar
Anbieter: Biblios, Frankfurt am main, HESSE, Deutschland
Zustand: New. PRINT ON DEMAND. Bestandsnummer des Verkäufers 18388700739
Anzahl: 4 verfügbar
Anbieter: moluna, Greven, Deutschland
Zustand: New. Dieser Artikel ist ein Print on Demand Artikel und wird nach Ihrer Bestellung fuer Sie gedruckt. Autor/Autorin: Yamen EmreEmre Yamen, studied Bachelor of Science Informatics at RWTH Aachen University. Master Student in Informatics and working on Machine Learning.Many relationships among data in several areas (such as computer vision, molec. Bestandsnummer des Verkäufers 293729627
Anzahl: Mehr als 20 verfügbar
Anbieter: buchversandmimpf2000, Emtmannsberg, BAYE, Deutschland
Taschenbuch. Zustand: Neu. Neuware -Many relationships among data in several areas (such as computer vision, molecular chemistry and pattern recognition) can be represented by graphs. In the machine learning setting, it is an important learning task to classify graph-structural data correctly. Typically, the established techniques for this setting proceed via graph kernels and neural-network classification. In this work, we explore end-to-end learning for graphs: the objective is to operate on the graph representations directly. The key idea of our approach is to use standard tools for graph canonization. We test the performance of this approach on several datasets arising from bioinformatics. In general, we find that the graph canonization, as such, does not improve the accuracy of the classification. A possible reason for this behavior is that the neural network ends up overfitting to the given adjacency matrix representation.VDM Verlag, Dudweiler Landstraße 99, 66123 Saarbrücken 52 pp. Englisch. Bestandsnummer des Verkäufers 9786202224178
Anzahl: 2 verfügbar
Anbieter: AHA-BUCH GmbH, Einbeck, Deutschland
Taschenbuch. Zustand: Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - Many relationships among data in several areas (such as computer vision, molecular chemistry and pattern recognition) can be represented by graphs. In the machine learning setting, it is an important learning task to classify graph-structural data correctly. Typically, the established techniques for this setting proceed via graph kernels and neural-network classification. In this work, we explore end-to-end learning for graphs: the objective is to operate on the graph representations directly. The key idea of our approach is to use standard tools for graph canonization. We test the performance of this approach on several datasets arising from bioinformatics. In general, we find that the graph canonization, as such, does not improve the accuracy of the classification. A possible reason for this behavior is that the neural network ends up overfitting to the given adjacency matrix representation. Bestandsnummer des Verkäufers 9786202224178
Anzahl: 1 verfügbar
Anbieter: preigu, Osnabrück, Deutschland
Taschenbuch. Zustand: Neu. End-to-end Graph Learning | Using Canonization | Emre Yamen | Taschenbuch | 52 S. | Englisch | 2019 | AV Akademikerverlag | EAN 9786202224178 | Verantwortliche Person für die EU: BoD - Books on Demand, In de Tarpen 42, 22848 Norderstedt, info[at]bod[dot]de | Anbieter: preigu. Bestandsnummer des Verkäufers 116800055
Anzahl: 5 verfügbar