inf535 - Computational Intelligence I (Veranstaltungsübersicht)

inf535 - Computational Intelligence I (Veranstaltungsübersicht)

Department für Informatik 6 KP
Modulteile Semesterveranstaltungen Wintersemester 2024/2025 Prüfungsleistung
Vorlesung
  • Eingeschränkter Zugang 2.01.535 - Evolution Strategies Lehrende anzeigen
    • Prof. Dr. Oliver Kramer
    • Jill Baumann

    Termine am Montag, 17.02.2025 - Freitag, 21.02.2025, Montag, 24.02.2025 - Dienstag, 25.02.2025 08:00 - 18:00
    The lecture on "Evolution Strategies" offers an in-depth exploration of optimization techniques that are pivotal in solving complex problems. It begins by introducing basic optimization concepts, setting the stage for more advanced strategies. The lecture delves into the (1+1)-ES, a simple evolution strategy that evolves solutions using one parent and one offspring per generation, illustrating the foundational mechanism of this approach. It further discusses the 1/5 success rule, a method for adapting the step size based on a target success rate, which helps maintain efficient progress. The concept of restarts is explored, emphasizing strategies to escape local optima and improve solution diversity. More complex is the (μ+λ)-ES, which involves multiple parents and offspring, enhancing the robustness and convergence rate of the strategy. Self-adaptation is highlighted as a crucial feature, allowing the algorithm to dynamically adjust its parameters to better suit the problem landscape. The lecture also covers the adaptation of the covariance matrix, a sophisticated technique that helps the algorithm learn and adapt to the shape of the optimization landscape. Experimental results are presented to showcase the practical applications and effectiveness of these strategies. Finally, benchmark functions described in the appendix serve as a standard for evaluating and comparing the performance of evolution strategies. In practical exercises, participants are introduced to Julia and all algorithms are programmed to facilitate hands-on learning and application. The course is worth 6 ECTS.
Übung
  • Eingeschränkter Zugang 2.01.535 - Evolution Strategies Lehrende anzeigen
    • Prof. Dr. Oliver Kramer
    • Jill Baumann

    Termine am Montag, 17.02.2025 - Freitag, 21.02.2025, Montag, 24.02.2025 - Dienstag, 25.02.2025 08:00 - 18:00
    The lecture on "Evolution Strategies" offers an in-depth exploration of optimization techniques that are pivotal in solving complex problems. It begins by introducing basic optimization concepts, setting the stage for more advanced strategies. The lecture delves into the (1+1)-ES, a simple evolution strategy that evolves solutions using one parent and one offspring per generation, illustrating the foundational mechanism of this approach. It further discusses the 1/5 success rule, a method for adapting the step size based on a target success rate, which helps maintain efficient progress. The concept of restarts is explored, emphasizing strategies to escape local optima and improve solution diversity. More complex is the (μ+λ)-ES, which involves multiple parents and offspring, enhancing the robustness and convergence rate of the strategy. Self-adaptation is highlighted as a crucial feature, allowing the algorithm to dynamically adjust its parameters to better suit the problem landscape. The lecture also covers the adaptation of the covariance matrix, a sophisticated technique that helps the algorithm learn and adapt to the shape of the optimization landscape. Experimental results are presented to showcase the practical applications and effectiveness of these strategies. Finally, benchmark functions described in the appendix serve as a standard for evaluating and comparing the performance of evolution strategies. In practical exercises, participants are introduced to Julia and all algorithms are programmed to facilitate hands-on learning and application. The course is worth 6 ECTS.
Hinweise zum Modul
Teilnahmevoraussetzungen

Grundlagen der Statistik
Prüfungszeiten

Am Ende der Vorlesungszeit
Prüfungsleistung Modul

Mündliche Prüfung oder Klausur
Kompetenzziele

Nach erfolgreichem Abschluss der Lehrveranstaltung sollen Studierende die Fähigkeit erworben haben, die vorgestellten Methoden sicher in Theorie und Praxis zu beherrschen. Dabei sollen entsprechende Problemstellungen der Optimierung und Datenanalyse von den Studierenden selbst erkannt, modelliert und die Methoden zielsicher eingesetzt werden.

Fachkompetenzen
Die Studierenden:

  • erkennen Optimierungsprobleme
  • implementieren einfache Algorithmen der heuristischen Optimierung - diskutieren kritisch Lösungsansätze und Methodenauswahl
  • vertiefen bekannte Kenntnisse aus Analysis und linearer Algebra

Methodenkompetenzen
Die Studierenden:

  • vertiefen Programmierkenntnisse
  • wenden Modellierungsfähigkeiten an
  • lernen den Zusammenhang zwischen Problemklasse und Methodenauswahl

Sozialkompetenzen
Die Studierenden:

  • implementieren gemeinsam in der Vorlesung vorgestellte Algorithmen
  • evaluieren eigene Lösungen und vergleichen diese mit denen Ihrer Kommilitonen

Selbstkompetenzen
Die Studierenden:

  • schätzen ihre Fach und Methodenkompetenz im Vergleich zu Kommilitonen ein.
  • erkennen die eigenen Grenzen passen ihr eigenes Vorgehen unter Bezugnahme der Methodenkompetenzen an nötige Anforderungen an