DeepAI
Log In Sign Up

Tree Neural Networks in HOL4

09/03/2020
by   Thibault Gauthier, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

12/02/2020

An Analytic Propositional Proof System on Graphs

In this paper we present a proof system that operates on graphs instead ...
10/25/2019

Deep Reinforcement Learning in HOL4

The paper describes an implementation of deep reinforcement learning thr...
11/02/2018

Automated Theorem Proving in Intuitionistic Propositional Logic by Deep Reinforcement Learning

The problem-solving in automated theorem proving (ATP) can be interprete...
05/30/2018

Automated proof synthesis for propositional logic with deep neural networks

This work explores the application of deep learning, a machine learning ...
06/20/2017

Towards Proof Synthesis Guided by Neural Machine Translation for Intuitionistic Propositional Logic

Inspired by the recent evolution of deep neural networks (DNNs) in machi...
11/08/2022

Perspectives on neural proof nets

In this paper I will present a novel way of combining proof net proof se...
09/13/2020

Understanding Boolean Function Learnability on Deep Neural Networks

Computational learning theory states that many classes of boolean formul...