MSc Presentation: Elre Oldewage
Posted by mriekert on Mon 05 Feb 2018, 14:37:52 Mon 05 Feb 2018, 14:37:52
When: 9 Feb at 13:00
Venue: IT 4-58
Title: The Perils of Particle Swarm Optimisation in High Dimensional Problem Spaces
Abstract:
Particle swarm optimisation (PSO) is a stochastic, population-based optimisation algorithm.
PSO has been applied successfully to a variety of domains. This thesis examines
the behaviour of PSO when applied to high dimensional optimisation problems. Empirical
experiments are used to illustrate the problems exhibited by the swarm, namely that
the particles are prone to leaving the search space and never returning. This thesis does
not intend to develop a new version of PSO specifically for high dimensional problems.
Instead, the thesis investigates why PSO fails in high dimensional search spaces.
Four different types of approaches are examined. The first is the application of velocity
clamping to prevent the initial velocity explosion and to keep particles inside the
search space. The second approach selects values for the acceleration coefficients and
inertia weights so that particle movement is restrained or so that the swarm follows particular
patterns of movement. The third introduces coupling between problem variables,
thereby reducing the swarm’s movement freedom and forcing the swarm to focus more on
certain subspaces within the search space. The final approach examines the importance
of initialisation strategies in controlling the swarm’s exploration to exploitation ratio.
The thesis shows that the problems exhibited by PSO in high dimensions, particularly
unwanted particle roaming, can not be fully mitigated by any of the techniques examined.
The thesis provides deeper insight into the reasons for PSO’s poor performance by
means of extensive empirical tests and theoretical reasoning.
Images
Links
Attachments
Additional News
- Department of Computer Science Receives a QS Ranking
- Standard Bank Technology Impact Challenge
- MSc Presentation: Stacey Omeleze
- Oral defense: Bennie Leonard
- Oral Defense: Prittish Dala
- Presentation by Dr Karen Renaud
- Dr. Mardé Helbig Selected as SAYAS Member
- UP Wins Annual Standard Bank Impact Challenge
- Coding Hat-Trick for the University of Pretoria
- COS 301 project prizes
- SAYAS Inauguration Ceremony
- Honours Induction
- MSc Presentation: Jade Abbott
- PhD oral presentation: Victor Kebande
- MSc Presentation: Elre Oldewage
- PhD oral defense: Tiaan Scheepers
- MSc Defence: Philip Trenwith
- MSc Defence: Ruan van Staden
- Prof Martin Olivier selected as a member of IAC
- Coding Competitions
- University of Pretoria participated in the Catalyst Coding Contest
- SIT Research Day
- Dr Linda Marshall Wins Departmental Teaching and Learning Award
- Autumn Graduation
- Coding Contests
- Dr Marde Helbig wins the TW Kambule-NSTF Emerging Researchers Award
- "We should all be Data Scientists"
- Another Dr in the department
- Deep Learning IndabaX to be hosted at UP
- Dr Vukosi Marivate selected for the DHET Future Professors Programme
- Mr Avinash Singh joins the Department as a Lecturer
- COVID-19: Computer science research group sets up databank to empower experts and citizens with accurate info
- International Collaboration on Verification of Multi-Agent Systems
- Dr Vukosi Marivate receives the "Mail and Guardian 200 Young South Africans 2020" award
- Call for COS301 projects now open
- Welcome Dr Thambo Nyathi
- Welcome Mr Werner Hauger