Machine Number Sense: A Dataset of Visual Arithmetic Problems for Abstract and Relational Reasoning

04/25/2020
by   Wenhe Zhang, et al.
8

As a comprehensive indicator of mathematical thinking and intelligence, the number sense (Dehaene 2011) bridges the induction of symbolic concepts and the competence of problem-solving. To endow such a crucial cognitive ability to machine intelligence, we propose a dataset, Machine Number Sense (MNS), consisting of visual arithmetic problems automatically generated using a grammar model–And-Or Graph (AOG). These visual arithmetic problems are in the form of geometric figures: each problem has a set of geometric shapes as its context and embedded number symbols. Solving such problems is not trivial; the machine not only has to recognize the number, but also to interpret the number with its contexts, shapes, and relations (e.g., symmetry) together with proper operations. We benchmark the MNS dataset using four predominant neural network models as baselines in this visual reasoning task. Comprehensive experiments show that current neural-network-based models still struggle to understand number concepts and relational operations. We show that a simple brute-force search algorithm could work out some of the problems without context information. Crucially, taking geometric context into account by an additional perception module would provide a sharp performance gain with fewer search steps. Altogether, we call for attention in fusing the classic search-based algorithms with modern neural networks to discover the essential number concepts in future research.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/09/2018

Two Is Harder To Recognize Than Tom: the Challenge of Visual Numerosity for Deep Learning

In the spirit of Turing test, we design and conduct a set of visual nume...
research
03/07/2019

RAVEN: A Dataset for Relational and Analogical Visual rEasoNing

Dramatic progress has been witnessed in basic vision tasks involving low...
research
11/14/2019

Attention on Abstract Visual Reasoning

Attention mechanisms have been boosting the performance of deep learning...
research
12/09/2021

PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning

A critical aspect of human visual perception is the ability to parse vis...
research
09/13/2018

Sequential Coordination of Deep Models for Learning Visual Arithmetic

Achieving machine intelligence requires a smooth integration of percepti...
research
06/07/2015

Visual Learning of Arithmetic Operations

A simple Neural Network model is presented for end-to-end visual learnin...
research
02/21/2022

A Review of Emerging Research Directions in Abstract Visual Reasoning

Abstract Visual Reasoning (AVR) problems are commonly used to approximat...

Please sign up or login with your details

Forgot password? Click here to reset