Tree Neural Networks in HOL4
Neural and Evolutionary Computing
2020-09-04 v1
Abstract
We present an implementation of tree neural networks within the proof assistant HOL4. Their architecture makes them naturally suited for approximating functions whose domain is a set of formulas. We measure the performance of our implementation and compare it with other machine learning predictors on the tasks of evaluating arithmetical expressions and estimating the truth of propositional formulas.
Keywords
Cite
@article{arxiv.2009.01827,
title = {Tree Neural Networks in HOL4},
author = {Thibault Gauthier},
journal= {arXiv preprint arXiv:2009.01827},
year = {2020}
}