1 / 8

Advancing Natural Computation: Evolutionary Computing and Neural Network Innovations

This project focuses on the exploration of natural computation through key areas such as evolutionary computation, meta-heuristic optimization, co-evolution, and neural network ensembles. We aim to develop innovative applications, including a software system using interactive evolution for user-centered designs and memetic algorithms for resource-constrained project scheduling. Additionally, we will create a neural network ensemble system for predicting software defects using the PROMISE Software Engineering Repository data. Students are encouraged to publish their findings in these exciting research domains.

shepry
Télécharger la présentation

Advancing Natural Computation: Evolutionary Computing and Neural Network Innovations

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Project Presentation 2010 Xin Yao CERCIA and Natural Computation Group

  2. Primary Interests • Evolutionary Computation • Meta-heuristic optimisation • Co-evolution • Neural network ensembles • Data mining • Applications

  3. Preparation • Prefer: “Introduction to Natural Computation” • Better: in addition to the above, “Machine Learning” • Even better: in addition to the above, “Evolutionary Computation”

  4. Example Areas

  5. Evolutionary Art / Interactive Evolutionary Computation • Develop a new software system that uses interactive evolution to evolve user-centred (personalised) 2-d patterns / art / designs

  6. Memetic Algorithms • Memetic algorithms are hybrid evolutionary and local search algorithms. • This project develops memetic algorithms for resource-constrained project scheduling problem.

  7. Software Defect Prediction / Software Cost Estimation • Develop a neural network ensemble system, based on negative correlation learning, to predict software defects or estimate software costs. • The data sets will come from the PROMISE Software Engineering Repository (http://promise.site.uottawa.ca/SERepository/)

  8. Summary • These are example areas only. Each area has multiple projects. Similar projects can be defined. • As long as a project is related to evolutionary computation or neural network ensembles, I will be very happy to supervise. • Encourage students to publish their work.

More Related