A Number Sense as an Emergent Property of the Manipulating Brain

12/08/2020
by   Neehar Kondapaneni, et al.
19

The ability to understand and manipulate numbers and quantities emerges during childhood, but the mechanism through which this ability is developed is still poorly understood. In particular, it is not known whether acquiring such a number sense is possible without supervision from a teacher. To explore this question, we propose a model in which spontaneous and undirected manipulation of small objects trains perception to predict the resulting scene changes. We find that, from this task, an image representation emerges that exhibits regularities that foreshadow numbers and quantity. These include distinct categories for zero and the first few natural numbers, a notion of order, and a signal that correlates with numerical quantity. As a result, our model acquires the ability to estimate the number of objects in the scene, as well as subitization, i.e. the ability to recognize at a glance the exact number of objects in small scenes. We conclude that important aspects of a facility with numbers and quantities may be learned without explicit teacher supervision.

READ FULL TEXT

page 3

page 6

page 8

research
12/02/2021

Recognizing Scenes from Novel Viewpoints

Humans can perceive scenes in 3D from a handful of 2D views. For AI agen...
research
12/02/2020

Curiosity-driven 3D Scene Structure from Single-image Self-supervision

Previous work has demonstrated learning isolated 3D objects (voxel grids...
research
11/23/2022

Bayesian Brain: Computation with Perception to Recognize 3D Objects

We mimic the cognitive ability of Human perception, based on Bayesian hy...
research
03/20/2022

Towards 3D Scene Understanding by Referring Synthetic Models

Promising performance has been achieved for visual perception on the poi...
research
09/06/2021

Binaural SoundNet: Predicting Semantics, Depth and Motion with Binaural Sounds

Humans can robustly recognize and localize objects by using visual and/o...
research
02/17/2017

Be Precise or Fuzzy: Learning the Meaning of Cardinals and Quantifiers from Vision

People can refer to quantities in a visual scene by using either exact c...
research
06/04/2019

Active Object Manipulation Facilitates Visual Object Learning: An Egocentric Vision Study

Inspired by the remarkable ability of the infant visual learning system,...

Please sign up or login with your details

Forgot password? Click here to reset