Feed forward gradient descent with momentum backpropagation neural network in tower defense targeting system
Date of Publication
2013
Document Type
Bachelor's Thesis
Degree Name
Bachelor of Science in Computer Science
Subject Categories
Computer Sciences
College
College of Computer Studies
Department/Unit
Computer Science
Thesis Adviser
Emerico Aguilar
Defense Panel Chair
Rafael Cabredo
Defense Panel Member
Solomon See
Abstract/Summary
Ever since the birth of Adobe Flash, tower defense games became more and more popular. In a tower defense game, you'll need to protect your base from incoming waves of enemies by building towers that will attack the enemies whenever it is in its range. There are different ways the tower can select which enemy it will attack, but none of which coordinates with each tower. In this thesis a new targeting system that uses an artificial neural network to select an enemy and coordinate with other towers was proposed. By comparing it to different implementations of a tower's targeting system, it was proved that an artificial neural network may be used in order to select a target creep and coordinate with other built towers, that results to a fewer life lost, higher killed enemies and more gold earned.
Abstract Format
html
Language
English
Format
Accession Number
TU18398
Shelf Location
Archives, The Learning Commons, 12F, Henry Sy Sr. Hall
Physical Description
xi, 61 leaves: ; illustrations (some colored) ; 28 cm.
Recommended Citation
Ramos, J. (2013). Feed forward gradient descent with momentum backpropagation neural network in tower defense targeting system. Retrieved from https://animorepository.dlsu.edu.ph/etd_bachelors/2633
