Arithmetic addition of two integers by deep image classification networks: experiments to quantify their autonomous reasoning ability

by   Shuaicheng Liu, et al.

The unprecedented performance achieved by deep convolutional neural networks for image classification is linked primarily to their ability of capturing rich structural features at various layers within networks. Here we design a series of experiments, inspired by children's learning of the arithmetic addition of two integers, to showcase that such deep networks can go beyond the structural features to learn deeper knowledge. In our experiments, a set of images is constructed, each image containing an arithmetic addition n+m in its central area, and several classification networks are then trained over a subset of images, using the sum as the label. Tests on the excluded images show that, as the image set gets larger, the networks have well learnt the law of arithmetic additions so as to build up their autonomous reasoning ability strongly. For instance, networks trained over a small percentage of images can classify a big majority of the remaining images correctly, and many arithmetic additions involving some integers that have never been seen during the training can also be solved correctly by the trained networks.


page 1

page 2

page 3

page 4

page 5


Committees of deep feedforward networks trained with few data

Deep convolutional neural networks are known to give good results on ima...

Diving deeper into mentee networks

Modern computer vision is all about the possession of powerful image rep...

A new method for binary classification of proteins with Machine Learning

In this work we set out to find a method to classify protein structures ...

Application of Convolutional Neural Network for Image Classification on Pascal VOC Challenge 2012 dataset

In this project we work on creating a model to classify images for the P...

Do Deep Neural Networks Capture Compositionality in Arithmetic Reasoning?

Compositionality is a pivotal property of symbolic reasoning. However, h...

The Tunnel Effect: Building Data Representations in Deep Neural Networks

Deep neural networks are widely known for their remarkable effectiveness...

Solving Arithmetic Word Problems with Transformers and Preprocessing of Problem Text

This paper outlines the use of Transformer networks trained to translate...

Please sign up or login with your details

Forgot password? Click here to reset