Image-to-image Neural Network for Addition and Subtraction of a Pair of Not Very Large Numbers
This is an incremental step in using neural networks for arithmetic tasks, but it has limited practical utility due to its narrow scope and error-prone nature.
The authors tackled the problem of performing basic arithmetic using a neural network by training a convolutional neural network to take an image of a simple mathematical expression and generate an image of the answer, but it only works with pairs of double-digit numbers for addition and subtraction and sometimes makes mistakes.
Looking back at the history of calculators, one can see that they become less functional and more computationally expensive over time. A modern calculator runs on a personal computer and is drawn at 60 fps only to help us click a few digits with a mouse pointer. A search engine is often used as a calculator, which means that nowadays we need the Internet just to add two numbers. In this paper, we propose to go further and train a convolutional neural network that takes an image of a simple mathematical expression and generates an image of an answer. This neural calculator works only with pairs of double-digit numbers and supports only addition and subtraction. Also, sometimes it makes mistakes. We promise that the proposed calculator is a small step for man, but one giant leap for mankind.