Combining Neuro-Evolution of Augmenting Topologies with Convolutional Neural Networks

Autor:	Hohenheim, Jan, Fischler, Mathias, Zarubica, Sara, Stucki, Jeremy
Rok vydání:	2022
Předmět:	Computer Science - Neural and Evolutionary Computing Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	Current deep convolutional networks are fixed in their topology. We explore the possibilites of making the convolutional topology a parameter itself by combining NeuroEvolution of Augmenting Topologies (NEAT) with Convolutional Neural Networks (CNNs) and propose such a system using blocks of Residual Networks (ResNets). We then explain how our suggested system can only be built once additional optimizations have been made, as genetic algorithms are way more demanding than training per backpropagation. On the way there we explain most of those buzzwords and offer a gentle and brief introduction to the most important modern areas of machine learning Comment: Unpublished
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2211.16978 Zobrazit plný text záznamu View this record from Arxiv