Deutsch Intern
    Data Science Chair

    Our Paper “Learning Mathematical Relations Using Deep Tree Models” has been accepted at IEEE ICMLA 2021

    09/29/2021

    Our paper “Learning Mathematical Relations Using Deep Tree Models” has been accepted at IEEE ICMLA 2021 special session “Machine Learning for Graphs”.

    In the paper, we evaluate if different recursive neural networks working on the parse trees of two mathematical terms are able to classify the relationship between them. For example, given the terms “x+x” and “2x”, the model should classify them as identical.

    We will update the news once the paper has finally been published at the conference. For now, we share the abstract with you:

    To the present day, computer algebra systems used for calculating mathematical relations on a symbolic level are mainly rule-based systems. Only recently, deep learning has been applied to the task of symbolic mathematics. Researchers succeeded in developing neural networks which can do symbolic calculations of the equivalence of multiple pairing of equations. However, the generator used to create mathematical terms in previous research has several drawbacks and as with all deep learning tasks, the quality of the data used for training the models has a significant impact on the quality of the results. In this work, we propose a new generator for polynomials. We use it to train several recursive neural networks to recognize the equivalence, derivative, or variable substitution between pairs of polynomials for the first time. Our results indicate that these mathematical relations are identifiable with the help of deep learning.

    Back