Search Results for author: Alexander Hagg

Found 9 papers, 1 papers with code

Expressivity of Parameterized and Data-driven Representations in Quality Diversity Search

1 code implementation10 May 2021 Alexander Hagg, Sebastian Berns, Alexander Asteroth, Simon Colton, Thomas Bäck

We consider multi-solution optimization and generative models for the generation of diverse artifacts and the discovery of novel solutions.

Designing Air Flow with Surrogate-assisted Phenotypic Niching

no code implementations10 May 2021 Alexander Hagg, Dominik Wilde, Alexander Asteroth, Thomas Bäck

In complex, expensive optimization domains we often narrowly focus on finding high performing solutions, instead of expanding our understanding of the domain itself.

Prediction of neural network performance by phenotypic modeling

no code implementations16 Jul 2019 Alexander Hagg, Martin Zaefferer, Jörg Stork, Adam Gaier

This difference, the phenotypic distance, can then be used to situate these networks into a common input space, allowing us to produce surrogate models which can predict the performance of neural networks regardless of topology.

Modeling User Selection in Quality Diversity

no code implementations16 Jul 2019 Alexander Hagg, Alexander Asteroth, Thomas Bäck

The initial phase in real world engineering optimization and design is a process of discovery in which not all requirements can be made in advance, or are hard to formalize.

Prototype Discovery using Quality-Diversity

no code implementations25 Jul 2018 Alexander Hagg, Alexander Asteroth, Thomas Bäck

An iterative computer-aided ideation procedure is introduced, building on recent quality-diversity algorithms, which search for diverse as well as high-performing solutions.

Dimensionality Reduction

Hierarchical Surrogate Modeling for Illumination Algorithms

no code implementations29 Mar 2017 Alexander Hagg

Evolutionary illumination is a recent technique that allows producing many diverse, optimal solutions in a map of manually defined features.

Evolving Parsimonious Networks by Mixing Activation Functions

no code implementations21 Mar 2017 Alexander Hagg, Maximilian Mensing, Alexander Asteroth

Neuroevolution methods evolve the weights of a neural network, and in some cases the topology, but little work has been done to analyze the effect of evolving the activation functions of individual nodes on network size, which is important when training networks with a small number of samples.

On Recognizing Transparent Objects in Domestic Environments Using Fusion of Multiple Sensor Modalities

no code implementations3 Jun 2016 Alexander Hagg, Frederik Hegger, Paul Plöger

Current object recognition methods fail on object sets that include both diffuse, reflective and transparent materials, although they are very common in domestic scenarios.

Object Recognition Transparent objects

Cannot find the paper you are looking for? You can Submit a new open access paper.