Autor: |
Santoro, A., Raposo, D., Barrett, D. G. T., Mateusz Malinowski, Pascanu, R., Battaglia, P., Lillicrap, T. |
Rok vydání: |
2017 |
Předmět: |
|
Zdroj: |
Scopus-Elsevier |
DOI: |
10.48550/arxiv.1706.01427 |
Popis: |
Relational reasoning is a central component of generally intelligent behavior, but has proven difficult for neural networks to learn. In this paper we describe how to use Relation Networks (RNs) as a simple plug-and-play module to solve problems that fundamentally hinge on relational reasoning. We tested RN-augmented networks on three tasks: visual question answering using a challenging dataset called CLEVR, on which we achieve state-of-the-art, super-human performance; text-based question answering using the bAbI suite of tasks; and complex reasoning about dynamic physical systems. Then, using a curated dataset called Sort-of-CLEVR we show that powerful convolutional networks do not have a general capacity to solve relational questions, but can gain this capacity when augmented with RNs. Our work shows how a deep learning architecture equipped with an RN module can implicitly discover and learn to reason about entities and their relations. |
Databáze: |
OpenAIRE |
Externí odkaz: |
|