Understanding Parameter Spaces Using Local Optima Networks
Offered By: Association for Computing Machinery (ACM) via YouTube
Course Description
Overview
Explore the complexities of parameter spaces in metaheuristics through a conference talk focusing on Particle Swarm Optimization (PSO). Delve into the use of Local Optima Networks (LONs) to visualize and analyze PSO parameter landscapes across various objective functions. Discover how the underlying objective function influences the structure of parameter landscapes, revealing unexpected complexities in PSO parameter tuning. Gain insights into the formalism of parameter landscapes and learn how LONs serve as an effective tool for analyzing and visualizing metaheuristic parameter landscapes. Follow the presentation's structure, covering the introduction, parameter landscape overview, PSO specifics, LONs, experimental results, and key observations from functions like Egg Holder and HyperEllipsoid.
Syllabus
Introduction
Overview
Parameter Landscape
pso
Local Optima Networks
Set C
Results
Egg Holder
HyperEllipsoid
Observations
Summary
Taught by
Association for Computing Machinery (ACM)
Related Courses
Deep Learning for Natural Language ProcessingUniversity of Oxford via Independent Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization
DeepLearning.AI via Coursera Deep Learning Part 1 (IITM)
Indian Institute of Technology Madras via Swayam Deep Learning - Part 1
Indian Institute of Technology, Ropar via Swayam Logistic Regression with Python and Numpy
Coursera Project Network via Coursera