{"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/tas-ternarized-neural-architecture-search-for","title":"TAS: Ternarized Neural Architecture Search for Resource-Constrained Edge Devices","arxiv_id":null,"date":"2022-03-14","proceeding":"Design, Automation and Test in Europe Conference (DATE) 2022 3","authors":["Mohammad Loni","Hamid Mousavi","Mohammad Riazati","Masoud Daneshtalab","and Mikael Sjodin"],"abstract":"Ternary Neural Networks (TNNs) compress network\r\nweights and activation functions into 2-bit representation resulting in remarkable network compression and energy efficiency.\r\nHowever, there remains a significant gap in accuracy between\r\nTNNs and full-precision counterparts. Recent advances in Neural\r\nArchitectures Search (NAS) promise opportunities in automated\r\noptimization for various deep learning tasks. Unfortunately, this\r\narea is unexplored for optimizing TNNs. This paper proposes\r\nTAS, a framework that drastically reduces the accuracy gap\r\nbetween TNNs and their full-precision counterparts by integrating quantization into the network design. We experienced\r\nthat directly applying NAS to the ternary domain provides\r\naccuracy degradation as the search settings are customized for\r\nfull-precision networks. To address this problem, we propose (i) a\r\nnew cell template for ternary networks with maximum gradient\r\npropagation; and (ii) a novel learnable quantizer that adaptively\r\nrelaxes the ternarization mechanism from the distribution of the\r\nweights and activation functions. Experimental results reveal that\r\nTAS delivers 2.64% higher accuracy and ≈2.8× memory saving\r\nover competing methods with the same bit-width resolution on the\r\nCIFAR-10 dataset. These results suggest that TAS is an effective\r\nmethod that paves the way for the efficient design of the next\r\ngeneration of quantized neural networks.","url_abs":"https://ieeexplore.ieee.org/document/9774615","url_pdf":"https://ieeexplore.ieee.org/document/9774615","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":"tas-ternarized-neural-architecture-search-for","repo_url":"https://github.com/HERO-MDH/TAS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"HERO-MDH/TAS","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":"2ddf12547e54fe5b830fbb077eba5c04f90ccec8d4c0ecb096cca9be499b9a3a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}