Solving Raven's Progressive Matrices with Multi-Layer Relation Networks

Marius Jahrens; Thomas Martinetz

doi:10.1109/IJCNN48605.2020.9207319

Solving Raven's Progressive Matrices with Multi-Layer Relation Networks

Institut für Neuro- und Bioinformatik

Abstract

Raven's Progressive Matrices are a benchmark originally designed to test the cognitive abilities of humans. It has recently been adapted to test relational reasoning in machine learning systems. For this purpose the so-called Procedurally Generated Matrices dataset was set up, which is so far one of the most difficult relational reasoning benchmarks. Here we show that deep neural networks are capable of solving this benchmark, reaching an accuracy of 98.0 percent over the previous state-of-the-art of 62.6 percent by combining Wild Relation Networks with Multi-Layer Relation Networks and introducing Magnitude Encoding, an encoding scheme designed for late fusion architectures.

Originalsprache	Englisch
Titel	2020 International Joint Conference on Neural Networks (IJCNN)
Herausgeber (Verlag)	IEEE
Erscheinungsdatum	07.2020
Aufsatznummer	9207319
ISBN (Print)	978-1-7281-6927-9
ISBN (elektronisch)	978-1-7281-6926-2
DOIs	https://doi.org/10.1109/IJCNN48605.2020.9207319
Publikationsstatus	Veröffentlicht - 07.2020
Veranstaltung	2020 International Joint Conference on Neural Networks - Virtual, Glasgow, Großbritannien / Vereinigtes Königreich Dauer: 19.07.2020 → 24.07.2020 Konferenznummer: 163566

Strategische Forschungsbereiche und Zentren

Querschnittsbereich: Intelligente Systeme
Zentren: Zentrum für Künstliche Intelligenz Lübeck (ZKIL)

DFG-Fachsystematik

409-05 Interaktive und intelligente Systeme, Bild- und Sprachverarbeitung, Computergraphik und Visualisierung

UN SDGs

Dieser Output leistet einen Beitrag zu folgendem(n) Ziel(en) für nachhaltige Entwicklung

Zugriff auf Dokument

10.1109/IJCNN48605.2020.9207319

Andere Dateien und Links

www.scopus.com

Zitieren

@inproceedings{fe6cf5e056424478ab98e869e3e89dcb,

title = "Solving Raven's Progressive Matrices with Multi-Layer Relation Networks",

abstract = "Raven's Progressive Matrices are a benchmark originally designed to test the cognitive abilities of humans. It has recently been adapted to test relational reasoning in machine learning systems. For this purpose the so-called Procedurally Generated Matrices dataset was set up, which is so far one of the most difficult relational reasoning benchmarks. Here we show that deep neural networks are capable of solving this benchmark, reaching an accuracy of 98.0 percent over the previous state-of-the-art of 62.6 percent by combining Wild Relation Networks with Multi-Layer Relation Networks and introducing Magnitude Encoding, an encoding scheme designed for late fusion architectures.",

author = "Marius Jahrens and Thomas Martinetz",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 2020 International Joint Conference on Neural Networks, IJCNN 2020 ; Conference date: 19-07-2020 Through 24-07-2020",

year = "2020",

month = jul,

doi = "10.1109/IJCNN48605.2020.9207319",

language = "English",

isbn = "978-1-7281-6927-9",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "IEEE",

booktitle = "2020 International Joint Conference on Neural Networks (IJCNN)",

}

Jahrens, M & Martinetz, T 2020, Solving Raven's Progressive Matrices with Multi-Layer Relation Networks. in 2020 International Joint Conference on Neural Networks (IJCNN)., 9207319, Proceedings of the International Joint Conference on Neural Networks, IEEE, 2020 International Joint Conference on Neural Networks, Glasgow, Großbritannien / Vereinigtes Königreich, 19.07.20. https://doi.org/10.1109/IJCNN48605.2020.9207319

TY - GEN

T1 - Solving Raven's Progressive Matrices with Multi-Layer Relation Networks

AU - Jahrens, Marius

AU - Martinetz, Thomas

N1 - Conference code: 163566

PY - 2020/7

Y1 - 2020/7

N2 - Raven's Progressive Matrices are a benchmark originally designed to test the cognitive abilities of humans. It has recently been adapted to test relational reasoning in machine learning systems. For this purpose the so-called Procedurally Generated Matrices dataset was set up, which is so far one of the most difficult relational reasoning benchmarks. Here we show that deep neural networks are capable of solving this benchmark, reaching an accuracy of 98.0 percent over the previous state-of-the-art of 62.6 percent by combining Wild Relation Networks with Multi-Layer Relation Networks and introducing Magnitude Encoding, an encoding scheme designed for late fusion architectures.

AB - Raven's Progressive Matrices are a benchmark originally designed to test the cognitive abilities of humans. It has recently been adapted to test relational reasoning in machine learning systems. For this purpose the so-called Procedurally Generated Matrices dataset was set up, which is so far one of the most difficult relational reasoning benchmarks. Here we show that deep neural networks are capable of solving this benchmark, reaching an accuracy of 98.0 percent over the previous state-of-the-art of 62.6 percent by combining Wild Relation Networks with Multi-Layer Relation Networks and introducing Magnitude Encoding, an encoding scheme designed for late fusion architectures.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85093830225&origin=inward&txGid=a8da8a941bf9a97db453332478f0a07a

U2 - 10.1109/IJCNN48605.2020.9207319

DO - 10.1109/IJCNN48605.2020.9207319

M3 - Conference contribution

SN - 978-1-7281-6927-9

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2020 International Joint Conference on Neural Networks (IJCNN)

PB - IEEE

T2 - 2020 International Joint Conference on Neural Networks

Y2 - 19 July 2020 through 24 July 2020

ER -

Solving Raven's Progressive Matrices with Multi-Layer Relation Networks

Abstract

Strategische Forschungsbereiche und Zentren

DFG-Fachsystematik

UN SDGs

Zugriff auf Dokument

Andere Dateien und Links

Fingerprint

Zitieren