Perceptron Learning in Engineering Design

Hojjat Adeli, Chung‐Hsing Yeh

Computer-Aided Civil and Infrastructure Engineering · 1989 · 248 citations · 15 references

Concepts

TL;DR

A perceptron is a four‑tuple entity that outputs a binary decision in the problem domain. The paper presents a self‑adjusting machine‑learning model for engineering design based on perceptron concepts. Structural design is cast as a perceptron without hidden units, and the model self‑adjusts internal control parameters. Experimental results are shown in tables and the study concludes with a comparison between perceptron and explanation‑based learning.

Abstract

A model of machine learning in engineering design is presented based on the concept of self‐adjustment of internal control parameters and perceptron. A perceptron is defined as a four‐tuple entity which can answer either “yes” or “no” in the problem domain. The problem of structural design is cast in a form that can be described by a perceptron without hidden units. Some results from our experimentation are presented in tabular form. The paper is concluded by a comparison of perceptron and explanation‐based learning.

References

15