University of Cambridge > Talks.cam > Machine Learning @ CUED > A simple neural network module for relational reasoning

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

A simple neural network module for relational reasoning

Download to your calendar using vCal

If you have a question about this talk, please contact Adrian Weller .

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.

https://arxiv.org/abs/1706.01427

This talk is part of the Machine Learning @ CUED series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Hybrid: Seminar room, SPRI & Zoom - email organiser for details ADC Theatre Average on weekdays: 9025.05619597 kWh

Other talks

Task performance predicts the substitution of feedforward by feedback drive in visual cortex Title to be confirmed External Seminar - Jenn Brophy TBC TBC Title to be confirmed Title and abstract tba
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity