- author = "Jiayu Liang and Hanqi Cao and Yaxin Lu and Mingming Su",
- title = "Architecture search of accurate and lightweight {CNNs} using genetic algorithm",
- journal = "Genetic Programming and Evolvable Machines",
- year = "2024",
- volume = "25",
- pages = "Article no 13",
- note = "Online first",
- keywords = "genetic algorithms, genetic programming, ANN, CNN architecture search, Evolutionary methods, Lightweight architecture, Image classification",
- ISSN = "1389-2576",
-
DOI = "
10.1007/s10710-024-09484-4",
- abstract = "Convolutional neural networks (CNNs) are popularly-used in various AI fields, yet the design of CNN architectures heavily depends on domain expertise. Evolutionary neural architecture search (ENAS) methods can search for neural architectures automatically using evolutionary computation algorithms, e.g. genetic algorithm. However, most existing ENAS methods solely focus on the network accuracy, which leads to large-sized networks to be evolved and huge cost in computation resources and search time. Even though there are ENAS works using multi-objective techniques to optimise time/resource-consuming. two new ENAS methods are designed, which aim to evolve both accurate and lightweight CNN architectures efficiently using genetic algorithm (GA). They are termed as GACNN WS (GA CNN Weighted Sum) and GACNN_LE (GA CNN Local Elitism) respectively. Specifically, GACNN_WS designs a weighted-sum fitness of two ...",
-
notes = "Is this GP?
Tianjin Key Laboratory of Autonomous Intelligent Technology and System, Tiangong University, Tianjin, 300387, China",
