DOC PREVIEW
UW-Madison ECE 539 - Artificial Neural Networks Final Project

This preview shows page 1-2 out of 6 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 6 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 6 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 6 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

ECE/CS/ME 539 Artificial Neural Networks Final ProjectA Comparison of a Learning Decision Tree and a 2-Layer Back-Propagation Neural Network on classifying a car purchase using a 2-Layer Back-Propagation Neural Network constructed in JavaIntroduction/MotivationDataResultsConclusionsECE/CS/ME 539ECE/CS/ME 539Artificial Neural Artificial Neural NetworksNetworksFinal ProjectFinal ProjectA Comparison of a Learning A Comparison of a Learning Decision Tree and a 2-Layer Decision Tree and a 2-Layer Back-Propagation Neural Back-Propagation Neural Network on classifying a car Network on classifying a car purchase using a 2-Layer Back-purchase using a 2-Layer Back-Propagation Neural Network Propagation Neural Network constructed in Javaconstructed in JavaSteve LudwigSteve Ludwig12-19-0312-19-03Introduction/MotivationIntroduction/MotivationStudied Decision Learning TreesStudied Decision Learning TreesSame purpose as pattern classifying BP Neural Same purpose as pattern classifying BP Neural NetsNetsWanted to compare/contrast using identical Wanted to compare/contrast using identical datadataBuilt own 2-layer back-propagation neural Built own 2-layer back-propagation neural network in Java with customizable network in Java with customizable attributesattributesDataDataLearning Tree uses text-based Learning Tree uses text-based attributes/valuesattributes/valuesConstructs ‘tree’ with nodes as attributesConstructs ‘tree’ with nodes as attributesLeaf nodes classify as positive or negativeLeaf nodes classify as positive or negativeHad to convert to numeric values for BP Neural Had to convert to numeric values for BP Neural NetNete.g. acceptable case = 1, unacceptable case = 0e.g. acceptable case = 1, unacceptable case = 0Could customize Neural Net parametersCould customize Neural Net parametersTried different learning rates, epochs, Tried different learning rates, epochs, permutation of train set (to avoid overfitting)permutation of train set (to avoid overfitting)ResultsResultsBoth Neural Net and Learning Tree Both Neural Net and Learning Tree had almost identical test set had almost identical test set classification ratesclassification ratesLearning Tree = 95.789 %Learning Tree = 95.789 %BP Neural Net = 95.105 %BP Neural Net = 95.105 %Learning Tree runs much faster, Learning Tree runs much faster, always consistentalways consistentNeural Net only consistent when train Neural Net only consistent when train set not permutatedset not permutatedConclusionsConclusionsLearning Tree works faster, great Learning Tree works faster, great accuracy, can use text-based accuracy, can use text-based attributesattributesBP Neural Net has more flexibility, BP Neural Net has more flexibility, can be modified to work better can be modified to work better (more hidden layers), still good (more hidden layers), still good classification rateclassification


View Full Document

UW-Madison ECE 539 - Artificial Neural Networks Final Project

Documents in this Course
Load more
Download Artificial Neural Networks Final Project
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Artificial Neural Networks Final Project and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Artificial Neural Networks Final Project 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?