{"id":{"repo_id":"brock","oai_identifier":"oai:brocku.scholaris.ca:10464/13709"},"canonical_url":"https://search.dev.ndltd.org/etd/brock/oai:brocku.scholaris.ca:10464/13709","repository":{"repo_id":"brock","name":"Brock University","base_url":"https://brocku.scholaris.ca/server/oai/request"},"display":{"title":"Deep Learning Concepts for Evolutionary Art","abstract":"A deep convolutional neural network (CNN) trained on millions of images forms a very high-level abstract overview of any given target image. Our primary goal is to use this high-level content information of a given target image to guide the automatic evolution of images. We use genetic programming (GP) to evolve procedural textures. We incorporate a pre-trained deep CNN model into the fitness. We are not performing any training, but rather, we pass a target image through the pre-trained deep CNN and use its the high-level representation as the fitness guide for evolved images. We develop a preprocessing strategy called Mean Minimum Matrix Strategy (MMMS) which reduces the dimensions and identifies the most relevant high-level activation maps. The technique using reduced activation matrices for a fitness shows promising results. GP is able to guide the evolution of textures such that they have shared characteristics with the target image. We also experiment with the fully connected “classifier” layers of the deep CNN. The evolved images are able to achieve high confidence scores from the deep CNN module for some tested target images. Finally, we implement our own shallow convolutional neural network with a fixed set of filters. Experiments show that the basic CNN had limited effectiveness, likely due to the lack of training. In conclusion, the research shows the potential for using deep learning concepts in evolutionary art. As deep CNN models become better understood, they will be able to be used more effectively for evolutionary art.","abstract_html":"A deep convolutional neural network (CNN) trained on millions of images forms a very high-level abstract overview of any given target image. Our primary goal is to use this high-level content information of a given target image to guide the automatic evolution of images. We use genetic programming (GP) to evolve procedural textures. We incorporate a pre-trained deep CNN model into the fitness. We are not performing any training, but rather, we pass a target image through the pre-trained deep CNN and use its the high-level representation as the fitness guide for evolved images. We develop a preprocessing strategy called Mean Minimum Matrix Strategy (MMMS) which reduces the dimensions and identifies the most relevant high-level activation maps. The technique using reduced activation matrices for a fitness shows promising results. GP is able to guide the evolution of textures such that they have shared characteristics with the target image. We also experiment with the fully connected “classifier” layers of the deep CNN. The evolved images are able to achieve high confidence scores from the deep CNN module for some tested target images. Finally, we implement our own shallow convolutional neural network with a fixed set of filters. Experiments show that the basic CNN had limited effectiveness, likely due to the lack of training. In conclusion, the research shows the potential for using deep learning concepts in evolutionary art. As deep CNN models become better understood, they will be able to be used more effectively for evolutionary art.","abstract_has_math":false,"creators":["Tanjil, Fazle"],"institution":"Brock University","degree_name":"M.Sc. Computer Science","degree_level":"Masters","degree_discipline":"Faculty of Mathematics and Science","degree_department":"Department of Computer Science","school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-09-28T18:55:06Z","date_published":"2018-09-28T18:55:06Z","updated_at":"2026-07-24T01:23:05Z","subjects":["deep learning","evolutionary art","genetic programming","convolutional neural networks"],"languages":["eng"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/10464/13709","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.department","label":"Department","values":["Department of Computer Science"]},{"key":"dc:creator","label":"Author","values":["Tanjil, Fazle"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2018-09-28T18:55:06Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2018-09-28T18:55:06Z"]},{"key":"dc:date.issued","label":"Date","values":["2018-09-28T18:55:06Z"]},{"key":"dc:type","label":"Dc Type","values":["Electronic Thesis or Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Faculty of Mathematics and Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.Sc. Computer Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Brock University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["deep learning","evolutionary art","genetic programming","convolutional neural networks"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/10464/13709"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["A deep convolutional neural network (CNN) trained on millions of images forms a very high-level abstract overview of any given target image. Our primary goal is to use this high-level content information of a given target image to guide the automatic evolution of images. We use genetic programming (GP) to evolve procedural textures. We incorporate a pre-trained deep CNN model into the fitness. We are not performing any training, but rather, we pass a target image through the pre-trained deep CNN and use its the high-level representation as the fitness guide for evolved images. We develop a preprocessing strategy called Mean Minimum Matrix Strategy (MMMS) which reduces the dimensions and identifies the most relevant high-level activation maps. The technique using reduced activation matrices for a fitness shows promising results. GP is able to guide the evolution of textures such that they have shared characteristics with the target image. We also experiment with the fully connected “classifier” layers of the deep CNN. The evolved images are able to achieve high confidence scores from the deep CNN module for some tested target images. Finally, we implement our own shallow convolutional neural network with a fixed set of filters. Experiments show that the basic CNN had limited effectiveness, likely due to the lack of training. In conclusion, the research shows the potential for using deep learning concepts in evolutionary art. As deep CNN models become better understood, they will be able to be used more effectively for evolutionary art."]},{"key":"dc:title","label":"Title","values":["Deep Learning Concepts for Evolutionary Art"]}]}],"canonical_facts":{"dc:contributor.department":["Department of Computer Science"],"dc:creator":["Tanjil, Fazle"],"dc:date.accessioned":["2018-09-28T18:55:06Z"],"dc:date.available":["2018-09-28T18:55:06Z"],"dc:date.issued":["2018-09-28T18:55:06Z"],"dc:description.abstract":["A deep convolutional neural network (CNN) trained on millions of images forms a very high-level abstract overview of any given target image. Our primary goal is to use this high-level content information of a given target image to guide the automatic evolution of images. We use genetic programming (GP) to evolve procedural textures. We incorporate a pre-trained deep CNN model into the fitness. We are not performing any training, but rather, we pass a target image through the pre-trained deep CNN and use its the high-level representation as the fitness guide for evolved images. We develop a preprocessing strategy called Mean Minimum Matrix Strategy (MMMS) which reduces the dimensions and identifies the most relevant high-level activation maps. The technique using reduced activation matrices for a fitness shows promising results. GP is able to guide the evolution of textures such that they have shared characteristics with the target image. We also experiment with the fully connected “classifier” layers of the deep CNN. The evolved images are able to achieve high confidence scores from the deep CNN module for some tested target images. Finally, we implement our own shallow convolutional neural network with a fixed set of filters. Experiments show that the basic CNN had limited effectiveness, likely due to the lack of training. In conclusion, the research shows the potential for using deep learning concepts in evolutionary art. As deep CNN models become better understood, they will be able to be used more effectively for evolutionary art."],"dc:identifier.uri":["http://hdl.handle.net/10464/13709"],"dc:language.iso":["eng"],"dc:subject":["deep learning","evolutionary art","genetic programming","convolutional neural networks"],"dc:title":["Deep Learning Concepts for Evolutionary Art"],"dc:type":["Electronic Thesis or Dissertation"],"thesis:degree_discipline":["Faculty of Mathematics and Science"],"thesis:degree_level":["Masters"],"thesis:degree_name":["M.Sc. Computer Science"],"thesis:institution_name":["Brock University"]},"updated_at":"2026-07-24T01:23:05Z"}