{"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/automatic-generation-of-neural-architecture","title":"Automatic Generation of Neural Architecture Search Spaces","arxiv_id":null,"date":"2021-11-21","proceeding":"AAAI Workshop CLeaR 2022 2","authors":["David Calhas","Vasco M. Manquinho","Ines Lynce"],"abstract":"Neural Architecture Search (NAS) is receiving growing attention as the need to remove the human bias from neural network models rises. There is extensive research in trying to beat state-of-the-art NAS algorithms. However, these advances do not focus directly on the search space these algorithms explore. Here, we propose a framework that encodes the structure of a convolutional neural network, respecting the arithmetical relation of the kernel and stride sizes with the input and output shapes. This framework consists of a formula with constraints that, if given the structure of the problem (input and output shapes), can produce specification properties of a neural architecture through a solver. We show that this methodology can assemble networks with arbitrary sizes and structures, that make for unique and uniform search spaces. To compare the resulting architectures, a metric that computes dissimilarity in terms of architectural structure is proposed. We empirically show that generating dissimilar architectures, implies dissimilarities in performance. In accordance, similar architectures are similar in performance.","url_abs":"https://openreview.net/forum?id=TCvkaP15O7e","url_pdf":"https://openreview.net/pdf?id=TCvkaP15O7e","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":"automatic-generation-of-neural-architecture","repo_url":"https://github.com/dcalhas/auto-nas-space","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}