Stitching for Neuroevolution: Recombining Deep Neural Networks without Breaking Them

A Guijt, D Thierens, T Alderliesten… - arXiv preprint arXiv …, 2024 - arxiv.org
Traditional approaches to neuroevolution often start from scratch. This becomes prohibitively
expensive in terms of computational and data requirements when targeting modern, deep …

Exploring the Search Space of Neural Network Combinations obtained with Efficient Model Stitching

A Guijt, D Thierens, T Alderliesten… - Proceedings of the …, 2024 - dl.acm.org
Machine learning models can be made more performant and their predictions more
consistent by creating an ensemble. Each neural network in an ensemble commonly …

On Solving Real-World Multi-Objective Human Resource Allocation Problem in Short-Term Employment Sector Using the Concept of Parameter-Less Population …

M Przewozniczek, PB Myszkowski, W Kosciukiewicz… - papers.ssrn.com
Frequently, various problem-dedicated optimizers are proposed when a real-life problem is
identified. Usually, the problem-dedicated mechanisms are based on the problem features …