{"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/approximate-fisher-information-matrix-to","title":"Approximate Fisher Information Matrix to Characterise the Training of Deep Neural Networks","arxiv_id":"1810.06767","date":"2018-10-16","proceeding":null,"authors":["Zhibin Liao","Tom Drummond","Ian Reid","Gustavo Carneiro"],"abstract":"In this paper, we introduce a novel methodology for characterising the\nperformance of deep learning networks (ResNets and DenseNet) with respect to\ntraining convergence and generalisation as a function of mini-batch size and\nlearning rate for image classification. This methodology is based on novel\nmeasurements derived from the eigenvalues of the approximate Fisher information\nmatrix, which can be efficiently computed even for high capacity deep models.\nOur proposed measurements can help practitioners to monitor and control the\ntraining process (by actively tuning the mini-batch size and learning rate) to\nallow for good training convergence and generalisation. Furthermore, the\nproposed measurements also allow us to show that it is possible to optimise the\ntraining process with a new dynamic sampling training approach that\ncontinuously and automatically change the mini-batch size and learning rate\nduring the training process. Finally, we show that the proposed dynamic\nsampling training approach has a faster training time and a competitive\nclassification accuracy compared to the current state of the art.","url_abs":"http://arxiv.org/abs/1810.06767v1","url_pdf":"http://arxiv.org/pdf/1810.06767v1.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":"approximate-fisher-information-matrix-to","repo_url":"https://github.com/zhibinliao89/fisher.info.mat.torch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.06767","atlas_url":"https://app.syntology.ai/?focus=1810.06767","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":"1810.06767"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1810.06767\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1810.06767"},"call":"get_concepts_for_paper(arxiv_id=\"1810.06767\")"}],"by_repo":[{"repo":"zhibinliao89/fisher.info.mat.torch","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":"98424762b21e32e19066b6aa5bc9ec3921a7255278469b356103838a4821c5ea","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}