writingpeter / SOLVE Public

Notifications You must be signed in to change notification settings
Fork 0
Star 2

Code for paper: Evolving Through the Looking Glass - Learning Improved Search Spaces with Variational Autoencoders

2 stars 0 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 11 Commits
coil		coil
coilfm		coilfm
stackedcoil		stackedcoil
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
README.txt		README.txt
__init__.py		__init__.py

Repository files navigation

Code Repository for SOLVE

Bentley, P. J., Lim, S. L., Gaier, A. and Tran, L. (2022) Evolving Through the Looking Glass: Learning Improved Search Spaces with Variational Autoencoders. In G. Rudolph et al. (Eds.): Proc of the 17th International Conference on Parallel Problem Solving From Nature (PPSN XVII). Sept 10-14th 2022. Dortmund Germany, LNCS 13398, pp. 371-384, 2022. doi.org/10.1007/978-3-031-14714-2_26

SOLVE extends the original COIL project (Constrained Optimization in Learned Latent Space) to extra criteria in addition to constraints, with layers/stacks and normalized flow VAE. Naming still reflects the original project.

Raw research code used to perform all experiments is in the `v0` branch.

Details of code contents and structure is located in README.txt

About

Code for paper: Evolving Through the Looking Glass - Learning Improved Search Spaces with Variational Autoencoders

genetic-algorithm variational-autoencoder generative-models latent-variable-evolution

Report repository

Releases

No releases published

Packages

No packages published

Languages

Python 100.0%