{"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/unsupervised-learning-on-neural-network","title":"Unsupervised Learning on Neural Network Outputs: with Application in Zero-shot Learning","arxiv_id":"1506.00990","date":"2015-06-02","proceeding":null,"authors":["Yao Lu"],"abstract":"The outputs of a trained neural network contain much richer information than\njust an one-hot classifier. For example, a neural network might give an image\nof a dog the probability of one in a million of being a cat but it is still\nmuch larger than the probability of being a car. To reveal the hidden structure\nin them, we apply two unsupervised learning algorithms, PCA and ICA, to the\noutputs of a deep Convolutional Neural Network trained on the ImageNet of 1000\nclasses. The PCA/ICA embedding of the object classes reveals their visual\nsimilarity and the PCA/ICA components can be interpreted as common visual\nfeatures shared by similar object classes. For an application, we proposed a\nnew zero-shot learning method, in which the visual features learned by PCA/ICA\nare employed. Our zero-shot learning method achieves the state-of-the-art\nresults on the ImageNet of over 20000 classes.","url_abs":"http://arxiv.org/abs/1506.00990v10","url_pdf":"http://arxiv.org/pdf/1506.00990v10.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":"unsupervised-learning-on-neural-network","repo_url":"https://github.com/yaolubrain/ULNNO","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[{"method_slug":"ica","method_name":"ICA"},{"method_slug":"pca","method_name":"PCA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1506.00990","atlas_url":"https://app.syntology.ai/?focus=1506.00990","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1506.00990"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1506.00990\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1506.00990"},"call":"get_concepts_for_paper(arxiv_id=\"1506.00990\")"}],"by_repo":[{"repo":"yaolubrain/ULNNO","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":"aee1722f9a3b9a5429c1304732b459419b83cfd3b7705dd7fa342b79b24ab795","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}