{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/genetic-cnn","title":"Genetic CNN","arxiv_id":"1703.01513","date":"2017-03-04","proceeding":"ICCV 2017 10","authors":["Lingxi Xie","Alan Yuille"],"abstract":"The deep Convolutional Neural Network (CNN) is the state-of-the-art solution\nfor large-scale visual recognition. Following basic principles such as\nincreasing the depth and constructing highway connections, researchers have\nmanually designed a lot of fixed network structures and verified their\neffectiveness.\n  In this paper, we discuss the possibility of learning deep network structures\nautomatically. Note that the number of possible network structures increases\nexponentially with the number of layers in the network, which inspires us to\nadopt the genetic algorithm to efficiently traverse this large search space. We\nfirst propose an encoding method to represent each network structure in a\nfixed-length binary string, and initialize the genetic algorithm by generating\na set of randomized individuals. In each generation, we define standard genetic\noperations, e.g., selection, mutation and crossover, to eliminate weak\nindividuals and then generate more competitive ones. The competitiveness of\neach individual is defined as its recognition accuracy, which is obtained via\ntraining the network from scratch and evaluating it on a validation set. We run\nthe genetic process on two small datasets, i.e., MNIST and CIFAR10,\ndemonstrating its ability to evolve and find high-quality structures which are\nlittle studied before. These structures are also transferrable to the\nlarge-scale ILSVRC2012 dataset.","url_abs":"http://arxiv.org/abs/1703.01513v1","url_pdf":"http://arxiv.org/pdf/1703.01513v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"genetic-cnn","repo_url":"https://github.com/gmontamat/gentun","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.01513","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}