Distance-based Kernels for Surrogate Model-based Neuroevolution

07/20/2018

∙

The topology optimization of artificial neural networks can be particularly difficult if the fitness evaluations require expensive experiments or simulations. For that reason, the optimization methods may need to be supported by surrogate models. We propose different distances for a suitable surrogate model, and compare them in a simple numerical test scenario.

READ FULL TEXT

Distance-based Kernels for Surrogate Model-based Neuroevolution

Improving NeuroEvolution Efficiency by Surrogate Model-based Optimization with Phenotypic Distance Kernels

Surrogate Models for Enhancing the Efficiency of Neuroevolution in Reinforcement Learning

Linear Combination of Distance Measures for Surrogate Models in Genetic Programming

A surrogate model for data-driven magnetic stray field calculations

SmOOD: Smoothness-based Out-of-Distribution Detection Approach for Surrogate Neural Networks in Aircraft Design

Data-efficient Neuroevolution with Kernel-Based Surrogate Models

A study on using image based machine learning methods to develop the surrogate models of stamp forming simulations

Distance-based Kernels for Surrogate Model-based Neuroevolution

Related Research

Improving NeuroEvolution Efficiency by Surrogate Model-based Optimization with Phenotypic Distance Kernels

Surrogate Models for Enhancing the Efficiency of Neuroevolution in Reinforcement Learning

Linear Combination of Distance Measures for Surrogate Models in Genetic Programming

A surrogate model for data-driven magnetic stray field calculations

SmOOD: Smoothness-based Out-of-Distribution Detection Approach for Surrogate Neural Networks in Aircraft Design

Data-efficient Neuroevolution with Kernel-Based Surrogate Models

A study on using image based machine learning methods to develop the surrogate models of stamp forming simulations