Classification of Iris Plant Using Perceptron Neural Network

Abstract

Classification is a prediction technique from the field of supervised learning where the goal is to predict group of membership for data instances. It is one of the fundamental tools of machine learning. Perceptron Neural Network is the first model of Artificial Neural Network implemented to simplify some problems of classification. In this paper we present an approach based on perceptron Neural Network to classified Iris Plant on the basis of the following measurements: sepal length, sepal width, petal length, and petal width. The architecture used in this work is multiclass perceptron with the One-Versus-All (OVA) strategy and the Stochastic gradient descent algorithm learning for training the perceptron.