Modelling the development of counting with memory-augmented neural networks

05/21/2021
by   Zack Dulberg, et al.
12

Learning to count is an important example of the broader human capacity for systematic generalization, and the development of counting is often characterized by an inflection point when children rapidly acquire proficiency with the procedures that support this ability. We aimed to model this process by training a reinforcement learning agent to select N items from a binary vector when instructed (known as the give-N task). We found that a memory-augmented modular network architecture based on the recently proposed Emergent Symbol Binding Network (ESBN) exhibited an inflection during learning that resembled human development. This model was also capable of systematic extrapolation outside the range of its training set - for example, trained only to select between 1 and 10 items, it could succeed at selecting 11 to 15 items as long as it could make use of an arbitrary count sequence of at least that length. The close parallels to child development and the capacity for extrapolation suggest that our model could shed light on the emergence of systematicity in humans.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 4

08/05/2020

A Robot that Counts Like a Child – a Developmental Model of Counting and Pointing

In this paper, a novel neuro-robotics model capable of counting real ite...
12/13/2020

A Memory-Augmented Neural Network Model of Abstract Rule Learning

Human intelligence is characterized by a remarkable ability to infer abs...
06/20/2017

Optimal modularity and memory capacity of neural networks

The neural network is a powerful computing framework that has been explo...
07/09/2019

Influence of Pointing on Learning to Count: A Neuro-Robotics Model

In this paper a neuro-robotics model capable of counting using gestures ...
04/20/2020

LRCN-RetailNet: A recurrent neural network architecture for accurate people counting

Measuring and analyzing the flow of customers in retail stores is essent...
06/12/2020

Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learning

This paper presents a neuro-symbolic agent that combines deep reinforcem...

Code Repositories

esbn-transformer

An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.