Using Convolutional Neural Networks to Analyze Function Properties from Images

Authors

  • Yoad Lewenberg The Hebrew University of Jerusalem, Israel
  • Yoram Bachrach Microsoft Research
  • Ian Kash Microsoft Research
  • Peter Key Microsoft Research

DOI:

https://doi.org/10.1609/aaai.v30i1.9843

Abstract

We propose a system for determining properties of mathematical functions given an image of their graph representation. We demonstrate our approach for two-dimensional graphs (curves of single variable functions) and three-dimensional graphs (surfaces of two variable functions), studying the properties of convexity and symmetry. Our method uses a Convolutional Neural Network which classifies functions according to these properties, without using any hand-crafted features. We propose algorithms for randomly constructing functions with convexity or symmetry properties, and use the images generated by these algorithms to train our network. Our system achieves a high accuracy on this task, even for functions where humans find it difficult to determine the function's properties from its image.

Downloads

Published

2016-03-05

How to Cite

Lewenberg, Y., Bachrach, Y., Kash, I., & Key, P. (2016). Using Convolutional Neural Networks to Analyze Function Properties from Images. Proceedings of the AAAI Conference on Artificial Intelligence, 30(1). https://doi.org/10.1609/aaai.v30i1.9843