Skip to content

This repository contains a multilayer perceptron predicting the potability of water.

Notifications You must be signed in to change notification settings

RyanFWebb/ds5020_mlp_project

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

51 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Team: Justine Cyr, Ben Darby, Ryan Webb
DS5020, Spring 2024
Professor: W Viles

An Overview of ANN/MLP: Analyzing Water Potability Data

Multilayer Perceptron for Water Potability Prediction - Paper

MLP Model in Colab Notebook

Project Topic: Multilayer Perceptron / Neural Network

  • This project will demonstrate the implementation of a Multi Layer Perceptron (MLP).

    1. It consists of an input layer of nodes that receive data.
    2. Hidden layer(s) of nodes that evaluate and specify the relationship between inputs and outputs.
    3. An output layer which provides approximated results using linear algebra.
  • This project is provided to showcase a method designed for classification, recognition, prediction and approximation.

  • To get started clone this repository onto your local network and navigate to the ds5020_mlp_project directory in your terminal.

  • type "make mlp" to run the mlp model

  • Repo Directories:

    • data: contains the data files for the mlp model
    • src: contains the source code for the mlp models

Bibliography

Multilayer Perceptron and Neural Networks

Introduction to Artificial Neural Networks

EEG signals classification using the K-means clustering and a multilayer perceptron neural network model

Deep learning using multilayer perception improves the diagnostic acumen of spirometry: a single-centre Canadian study

A survey on neural networks for (cyber-) security and (cyber-) security of neural networks

An intelligent bankruptcy prediction model using a multilayer perceptron

About

This repository contains a multilayer perceptron predicting the potability of water.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 98.6%
  • Makefile 1.4%