/Iris-SVMvsSimpleNN-comparison

A comparative analysis between Support Vector Machines (SVM) and simple Neural Networks (NN) for classification of Iris dataset.

Primary LanguageJupyter Notebook

Iris Dataset Analysis Repository

GitHub

Introduction

Welcome to the Iris Dataset Analysis Repository! This repository contains code and documentation for analyzing the Iris dataset using machine learning techniques. The primary focus is on data visualization, training Support Vector Machine (SVM) models, and building a neural network for classification tasks.

Dataset

The Iris dataset is a classic dataset in the field of machine learning. It consists of 150 samples of iris flowers, with each sample containing measurements of sepal and petal length and width, as well as the species of the iris. There are three species in the dataset: Iris-setosa, Iris-versicolor, and Iris-virginica.

Features

  • Data visualization using t-SNE.
  • Training Support Vector Machine (SVM) models.
  • Building a neural network for classification tasks.

Installation

Clone the repository:

git clone https://github.com/yourusername/iris-dataset-analysis.git

Usage

Load the raw data and visualize it using t-SNE. Train SVM models for classification tasks. Build a neural network and evaluate its performance.

Results

SVM models accuracy: 96% (linear), 100% (non-linear). Neural network accuracy: 97.77%.

License

This project is licensed under the MIT License.