---
title: "Learning Equation Solving Methods From Examples"
authors:
  - "Bernard Silver"
doi: ""
url: "https://ijcai.org/proceedings/1983/104"
pdf: "https://ijcai.org/proceedings/1983/0104.pdf"
venue: "Proceedings of the Eighth International Joint Conference on Artificial Intelligence"
year: 1983
pages: "429-430"
track: "Learning and Knowledge Acquisition"
keywords:
---

# Learning Equation Solving Methods From Examples

Bernard Silver

*Proceedings of the Eighth International Joint Conference on Artificial Intelligence*, pages 429-430.

## Abstract

This J:Sper describes LP*, a program that learns new techniques for solving equations by examining worked examples. Unlike most of the work in this field, e.g. (Neves, 1978), where the equations used have been very simple, LP uses complex equations, see below. LP can learn from one example, using concepts from the planning field. In order to be able to successfully use a new technique, LP learns many different types of information. To learn new rewrite rules, LP cOmJ:Sres consecutive lines in the worked example, finding differences between them. It also learns the strategic purpose of the stepa, by considering the worked example as a type of plan for solving the equation. LP extracts the necessary information, and builds a plan which is stored for future use. LP executes the plan in a flexible way to solve new equations.