- author = "Zhe Li and Xuehan Xiong and Zhou Ren and Ning Zhang and Xiaoyu Wang and Tianbao Yang",
- title = "An Aggressive Genetic Programming Approach for Searching Neural Network Structure Under Computational Constraints",
- howpublished = "arXiv",
- year = "2018",
- month = "3 " # jun,
- keywords = "genetic algorithms, genetic programming, ANN",
- bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/corr/corr1806.html#abs-1806-00851",
-
URL = "
http://arxiv.org/abs/1806.00851",
- size = "16 pages",
- abstract = "Recently, there emerged revived interests of designing automatic programs (e.g., using genetic/evolutionary algorithms) to optimise the structure of Convolutional Neural Networks (CNNs) for a specific task. The challenge in designing such programs lies in how to balance between large search space of the network structures and high computational costs. Existing works either impose strong restrictions on the search space or use enormous computing resources. In this paper, we study how to design a genetic programming approach for optimising the structure of a CNN for a given task under limited computational resources yet without imposing strong restrictions on the search space. To reduce the computational costs, we propose two general strategies that are observed to be helpful: (i) aggressively selecting strongest individuals for survival and reproduction, and killing weaker individuals at a very early age; (ii) increasing mutation frequency to encourage diversity and faster evolution. The combined strategy with additional optimisation techniques allows us to explore a large search space but with affordable computational costs. Our results on standard benchmark datasets (MNIST, SVHN, CIFAR-10, CIFAR-100) are competitive to similar approaches with significantly reduced computational costs.",
-
notes = "The University of Iowa
journals/corr/abs-1806-00851",
