Genetic and Evolutionary Computation Conference 2017

Die Genetic and Evolutionary Computation Conference (GECCO) ist eine der führenden internationalen Fachkonferenzen für evolutionäre Optimierung und Treffpunkt der Special Interest Group for Genetic and Evolutionary Computation (SIGEVO).

Die Konferenz wurde 1999 ins Leben gerufen und befasst sich mit neuesten Forschungsergebnissen, u.a. aus den Bereichen Genetic Programming, Schwarmintelligenz, Komplexe Systeme und Evolutionary Machine Learning.

Die GECCO 2017

Im Jahr 2017 fand die 19. GECCO in der deutschen Hauptstadt Berlin statt. An fünf Konferenztagen befassten sich 24 Workshops/Tutorials sowie 13 Schwerpunktprogramme in über 180 Vorträgen mit dem Themenfeld Genetic and Evolutionary Computation. Die unterschiedlichen Vorträge wurden von den weltweit führenden Forschern des jeweiligen Fachgebietes gehalten.

Unsere Interessenschwerpunkte

Wir sind bei folgenden Veranstaltungen, Vorträgen und Workshops vor Ort und freuen uns über den fachlichen Austausch:

Workshops und Tutorials

  • Automated Offline Design of Algorithms
  • Hyper-heuristics
  • Evolutionary Computation for the Automated Design of Algorithms
  • Model-Based Evolutionary Algorithms
  • Evolutionary Rule-Based Machine Learning
  • Solving Complex Problems with Coevolutionary Algorithms
  • Evolution of Neural Networks

Hauptkonferenz

Montag
Keynote
  • Computational Approaches in Cancer Genomics
Session 1: Evolutionary Machine Learning
  • Theoretical XCS parameter settings of learning accurate classifiers Paper
  • Particle swarm optimization for hyper-parameter selection in deep neural networks Paper
  • Biogeography-based rule mining for classification Paper
  • Evolving parsimonious networks by mixing activation functions Paper
Session 2: Theory
  • Upper bounds on the runtime of the univariate marginal distribution algorithm on onemax Paper
  • When is it beneficial to reject improvements? Paper
  • Running time analysis of the (1+1)-EA for onemax and leadingones under bit-wise noise Paper
  • The (1+λ) evolutionary algorithm with self-adjusting mutation rate Paper
Session 3: Evolutionary Machine Learning
  • Toward the automated analysis of complex diseases in genome-wide association studies using genetic programming Paper
  • Accelerating coevolution with adaptive matrix factorization Paper
  • Evolving memory-augmented neural architecture for deep memory problems Paper
  • A genetic programming approach to designing convolutional neural network architectures Paper
Dienstag
Keynote
  • Evolving Brains in Evolving Environments
Session 1: Genetic Programming
  • Improving generalization of evolved programs through automatic simplification Paper
  • How noisy data affects geometric semantic genetic programming Paper
  • Counterexample-driven genetic programming Paper
Session 2: Evolutionary Machine Learning
  • Automatic adjustment of selection pressure based on range of reward in learning classifier system Paper
  • Multiple imputation and genetic programming for classification with incomplete data Paper
  • Towards the evolution of multi-layered neural networks: a dynamic structured grammatical evolution approach Paper
  • Neuroevolution on the edge of chaos Paper
Session 3: Theory & Evolutionary Numerical Optimization
  • TPAM: a simulation-based model for quantitatively analyzing parameter adaptation methods Paper
  • Deriving and improving CMA-ES with information geometric trust regions Paper
  • Exploiting linkage information in real-valued optimization with the real-valued gene-pool optimal mixing evolutionary algorithm Paper
  • Runtime analysis of the (1 + (λ, λ)) genetic algorithm on random satisfiable 3-CNF formulas Paper
Mittwoch
Session 1: Theory
  • Unknown solution length problems with no asymptotically optimal run time Paper
  • Reoptimization times of evolutionary algorithms on linear functions under dynamic uniform constraints Paper
  • Island models meet rumor spreading Paper

Montag bis Freitag von 9 bis 22 Uhr stehen wir Ihnen persönlich und diskret zur Verfügung.
Rufen Sie uns an oder senden Sie uns eine E-Mail, unter Wir freuen uns auf Ihre Kontaktaufnahme.