Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Accelerated cooperative co-evolution on multi-core architectures
The Cooperative Co-Evolution (CC) model has been used in Evolutionary Computation (EC) to optimize the training of artificial neural networks (ANNs). This architecture has proven to be a useful extension to domains such as Neuro-Evolution (NE), which is the training of ANNs using concepts of natural...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Department of Computer Science
2019
|
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613310375952384 |
|---|---|
| access_status_str | Open Access |
| author | Moyo, Edmore |
| author2 | Kuttel, Michelle |
| author_browse | Kuttel, Michelle Moyo, Edmore |
| author_facet | Kuttel, Michelle Moyo, Edmore |
| author_sort | Moyo, Edmore |
| collection | Thesis |
| description | The Cooperative Co-Evolution (CC) model has been used in Evolutionary Computation (EC) to optimize the training of artificial neural networks (ANNs). This architecture has proven to be a useful extension to domains such as Neuro-Evolution (NE), which is the training of ANNs using concepts of natural evolution. However, there is a need for real-time systems and the ability to solve more complex tasks which has prompted a further need to optimize these CC methods. CC methods consist of a number of phases, however the evaluation phase is still the most compute intensive phase, for some complex tasks taking as long as weeks to complete. This study uses NE as a test case study and we design a parallel CC processing framework and implement the optimized serial and parallel versions using the Go programming language. Go is a multi-core programming language with first-class constructs, channels and goroutines, that make it well suited to parallel programming. Our study focuses on Enforced Subpopulations (ESP) for single-agent systems and Multi-Agent ESP for multi-agent systems. We evaluate the parallel versions in the benchmark tasks; double pole balancing and prey-capture, for single and multi-agent systems respectively, in tasks of increasing complexity. We observe a maximum speed-up of 20x for the parallel Multi-Agent ESP implementation over our single core optimized version in the prey-capture task and a maximum speedup of 16x for ESP in the harder version of double pole balancing task. We also observe linear speed-ups for the difficult versions of the tasks for a certain range of cores, indicating that the Go implementations are efficient and that the parallel speed-ups are better for more complex tasks. We find that in complex tasks, the Cooperative Co-Evolution Neuro-Evolution (CCNE) methods are amenable to multi-core acceleration, which provides a basis for the study of even more complex CC methods in a wider range of domains. |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/29999 |
| institution | University of Cape Town (South Africa) |
| language | eng |
| last_indexed | 2026-06-10T12:34:06.076Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository |
| publishDate | 2019 |
| publishDateRange | 2019 |
| publishDateSort | 2019 |
| publisher | Department of Computer Science |
| publisherStr | Department of Computer Science |
| record_format | dspace |
| source_str | UCTD — University of Cape Town Open Access Repository |
| spelling | oai:open.uct.ac.za:11427/29999 Accelerated cooperative co-evolution on multi-core architectures Moyo, Edmore Kuttel, Michelle Nitschke, Geoff Stuart The Cooperative Co-Evolution (CC) model has been used in Evolutionary Computation (EC) to optimize the training of artificial neural networks (ANNs). This architecture has proven to be a useful extension to domains such as Neuro-Evolution (NE), which is the training of ANNs using concepts of natural evolution. However, there is a need for real-time systems and the ability to solve more complex tasks which has prompted a further need to optimize these CC methods. CC methods consist of a number of phases, however the evaluation phase is still the most compute intensive phase, for some complex tasks taking as long as weeks to complete. This study uses NE as a test case study and we design a parallel CC processing framework and implement the optimized serial and parallel versions using the Go programming language. Go is a multi-core programming language with first-class constructs, channels and goroutines, that make it well suited to parallel programming. Our study focuses on Enforced Subpopulations (ESP) for single-agent systems and Multi-Agent ESP for multi-agent systems. We evaluate the parallel versions in the benchmark tasks; double pole balancing and prey-capture, for single and multi-agent systems respectively, in tasks of increasing complexity. We observe a maximum speed-up of 20x for the parallel Multi-Agent ESP implementation over our single core optimized version in the prey-capture task and a maximum speedup of 16x for ESP in the harder version of double pole balancing task. We also observe linear speed-ups for the difficult versions of the tasks for a certain range of cores, indicating that the Go implementations are efficient and that the parallel speed-ups are better for more complex tasks. We find that in complex tasks, the Cooperative Co-Evolution Neuro-Evolution (CCNE) methods are amenable to multi-core acceleration, which provides a basis for the study of even more complex CC methods in a wider range of domains. 2019-05-10T10:51:51Z 2019-05-10T10:51:51Z 2018 2019-05-10T08:43:02Z Master Thesis Masters MSc http://hdl.handle.net/11427/29999 eng application/pdf Department of Computer Science Faculty of Science |
| spellingShingle | Moyo, Edmore Accelerated cooperative co-evolution on multi-core architectures |
| thesis_degree_str | Master's |
| title | Accelerated cooperative co-evolution on multi-core architectures |
| title_full | Accelerated cooperative co-evolution on multi-core architectures |
| title_fullStr | Accelerated cooperative co-evolution on multi-core architectures |
| title_full_unstemmed | Accelerated cooperative co-evolution on multi-core architectures |
| title_short | Accelerated cooperative co-evolution on multi-core architectures |
| title_sort | accelerated cooperative co evolution on multi core architectures |
| url | http://hdl.handle.net/11427/29999 |
| work_keys_str_mv | AT moyoedmore acceleratedcooperativecoevolutiononmulticorearchitectures |