{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/improving-neural-architecture-search-image","title":"Improving Neural Architecture Search Image Classifiers via Ensemble Learning","arxiv_id":"1903.06236","date":"2019-03-14","proceeding":null,"authors":["Vladimir Macko","Charles Weill","Hanna Mazzawi","Javier Gonzalvo"],"abstract":"Finding the best neural network architecture requires significant time,\nresources, and human expertise. These challenges are partially addressed by\nneural architecture search (NAS) which is able to find the best convolutional\nlayer or cell that is then used as a building block for the network. However,\nonce a good building block is found, manual design is still required to\nassemble the final architecture as a combination of multiple blocks under a\npredefined parameter budget constraint. A common solution is to stack these\nblocks into a single tower and adjust the width and depth to fill the parameter\nbudget. However, these single tower architectures may not be optimal. Instead,\nin this paper we present the AdaNAS algorithm, that uses ensemble techniques to\ncompose a neural network as an ensemble of smaller networks automatically.\nAdditionally, we introduce a novel technique based on knowledge distillation to\niteratively train the smaller networks using the previous ensemble as a\nteacher. Our experiments demonstrate that ensembles of networks improve\naccuracy upon a single neural network while keeping the same number of\nparameters. Our models achieve comparable results with the state-of-the-art on\nCIFAR-10 and sets a new state-of-the-art on CIFAR-100.","url_abs":"http://arxiv.org/abs/1903.06236v1","url_pdf":"http://arxiv.org/pdf/1903.06236v1.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":"improving-neural-architecture-search-image","repo_url":"https://github.com/tensorflow/adanet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"ensemble-learning","task_name":"Ensemble Learning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"ASANas","rank_in_archive_order":62,"of":211,"metrics":{"Percentage correct":"85.42"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"tensorflow/adanet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"8731f856661bac6849f8ad90add1c66fad1b009211c336d1012737cc50772a55","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}