{"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/deep-linear-discriminant-analysis","title":"Deep Linear Discriminant Analysis","arxiv_id":"1511.04707","date":"2015-11-15","proceeding":null,"authors":["Matthias Dorfer","Rainer Kelz","Gerhard Widmer"],"abstract":"We introduce Deep Linear Discriminant Analysis (DeepLDA) which learns\nlinearly separable latent representations in an end-to-end fashion. Classic LDA\nextracts features which preserve class separability and is used for\ndimensionality reduction for many classification problems. The central idea of\nthis paper is to put LDA on top of a deep neural network. This can be seen as a\nnon-linear extension of classic LDA. Instead of maximizing the likelihood of\ntarget labels for individual samples, we propose an objective function that\npushes the network to produce feature distributions which: (a) have low\nvariance within the same class and (b) high variance between different classes.\nOur objective is derived from the general LDA eigenvalue problem and still\nallows to train with stochastic gradient descent and back-propagation. For\nevaluation we test our approach on three different benchmark datasets (MNIST,\nCIFAR-10 and STL-10). DeepLDA produces competitive results on MNIST and\nCIFAR-10 and outperforms a network trained with categorical cross entropy (same\narchitecture) on a supervised setting of STL-10.","url_abs":"http://arxiv.org/abs/1511.04707v5","url_pdf":"http://arxiv.org/pdf/1511.04707v5.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":"deep-linear-discriminant-analysis","repo_url":"https://github.com/Gary-Shi/DeepLDA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-linear-discriminant-analysis","repo_url":"https://github.com/vahidoox/deeplda","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"}],"methods":[{"method_slug":"lda","method_name":"LDA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1511.04707","atlas_url":"https://app.syntology.ai/?focus=1511.04707","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":"1511.04707"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1511.04707\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1511.04707"},"call":"get_concepts_for_paper(arxiv_id=\"1511.04707\")"}],"by_repo":[{"repo":"Gary-Shi/DeepLDA","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"vahidoox/deeplda","kind":"listed","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":"6cdfd85f29258d1bf1a8da19ef3af4406234d28685ebb6019a7abc101421a415","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}