HackerPapers

arXiv:1706.01427cs.CL

A simple neural network module for relational reasoning

Adam Santoro, David Raposo, David G. T. Barrett, Mateusz Malinowski, Razvan Pascanu, Peter Battaglia, Timothy Lillicrap

Abstract

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.

arXiv comments
Journal reference
DOI
Subjects
cs.CLComputation and Language cs.LGMachine Learning

On Hacker News

Linked by 6 identifiable commenters in 6 comments across 5 threads, from Jun 2017 to Jul 2026. Found in 1 HN submission from Jun 2017 to Jun 2017. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments5 threads

  1. 30papers.com – Ilya's 30 essential ML papers, in a beginner friendly format 2 comments

    • https://colah.github.io/posts/2015-08-Understanding-LSTMs/ https://papers.nips.cc/paper/2012/hash/c399862d3b9d6b76c8436... https://papers.nips.cc/paper_files/paper/2012/file/c399862d3... https://arxiv.org/pdf/1512.03385 https://arxiv.org/pdf/1511.07122…

      gooobView on HNParent context

    • No need stupid moving texts. CS231n: Convolutional Neural Networks for Visual Recognition - https://cs231n.github.io/ The Unreasonable Effectiveness of Recurrent Neural Networks - https://karpathy.github.io/2015/05/21/rnn-effectiveness/ Understanding LSTM Networks…

      cute_boiView on HNParent context

  2. Ilya Sutskever: “If you learn all of these, you’ll know 90% of what matters” 1 comment

    • a backup just in case https://nlp.seas.harvard.edu/annotated-transformer/ https://scottaaronson.blog/?p=762 https://karpathy.github.io/2015/05/21/rnn-effectiveness/ https://colah.github.io/posts/2015-08-Understanding-LSTMs/ https://arxiv.org/pdf/1409.2329.pdf…

      is_trueView on HNParent context

  3. DeepMind AI is as fast as humans at solving previously unseen tasks 1 comment

    • Nah. They need to walk before they can run. In 2016, their system could locate objects in a scene[0]. In 2017, it could answer questions about a scene[1]. In 2018, it could infer how a scene looks from any angle using a couple photos[2]. Now, it can perform inference tasks in a…

      espadrineView on HNParent context

  4. The Machine Learning Race Is Really a Data Race 1 comment

    • Sure. I don't have any holistic survey to prove my point, but an example of recent progress in terms of sample efficiency is this paper[0]. Derivatives of this paper have been used to solve Sudoku[1], Starcraft II[2] and more [3]. This paper enabled more efficient use of data by…

      yonkshiView on HNParent context

  5. Exploring LSTMs 1 comment

    • Yes, one of the links is from DeepMind: "A simple neural network module for relational reasoning" https://arxiv.org/abs/1706.01427 Another one is from Thomas Kipf: "Graph Convolutional Matrix Completion" https://arxiv.org/abs/1706.02263

      visargaView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.