Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Distributed Evolutionary Computation using REST


Published on

Presentation for IWDECIE within CEC2011

Published in: Technology
  • Be the first to comment

Distributed Evolutionary Computation using REST

  1. 1. Distributed Evolutionary Computation using REST P.A. Castillo, M.G. Arenas, A.M. Mora, J.L.J. Laredo, G. Romero,V.M Rivas J.J. Merelo GeNeura Group
  2. 2. If you've been paying attention REST beats other web-services implementations: lighter, more scalable
  3. 3. Let's put it to work Using a single server, different clients (master/slave implementation)
  4. 4. What problem? <ul><li>Optimization of topology + initial weights for a multilayer perceptron: G-Prop algorithm (Castillo et al., 1999)
  5. 5. Evaluation lengthy and time-consuming </li></ul>
  6. 6. Client/server implementation
  7. 7. Old McREST had a farm <ul><li>But we will not be using it for this.
  8. 8. Populations running in parallel on clients and use REST server for communication.
  9. 9. Hope to achieve better scaling that way. </li></ul>
  10. 10. Reminder: REST architecture Send chromosomes to the server Request chromosomes Send chromosomes Get evaluated chromosomes Uses PerlDancer Uses Algorithm::Evolutionary
  11. 11. Evolutionary algorithm parameters
  12. 12. Experimental results
  13. 13. Speedup nodes speedup
  14. 14. REST your parallelization in peace Just add clients!
  15. 15. Open source your science!
  16. 16. Any question?