{"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/bayesian-convolutional-neural-networks-with","title":"Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference","arxiv_id":"1506.02158","date":"2015-06-06","proceeding":null,"authors":["Yarin Gal","Zoubin Ghahramani"],"abstract":"Convolutional neural networks (CNNs) work well on large datasets. But\nlabelled data is hard to collect, and in some applications larger amounts of\ndata are not available. The problem then is how to use CNNs with small data --\nas CNNs overfit quickly. We present an efficient Bayesian CNN, offering better\nrobustness to over-fitting on small data than traditional approaches. This is\nby placing a probability distribution over the CNN's kernels. We approximate\nour model's intractable posterior with Bernoulli variational distributions,\nrequiring no additional model parameters.\n  On the theoretical side, we cast dropout network training as approximate\ninference in Bayesian neural networks. This allows us to implement our model\nusing existing tools in deep learning with no increase in time complexity,\nwhile highlighting a negative result in the field. We show a considerable\nimprovement in classification accuracy compared to standard techniques and\nimprove on published state-of-the-art results for CIFAR-10.","url_abs":"http://arxiv.org/abs/1506.02158v6","url_pdf":"http://arxiv.org/pdf/1506.02158v6.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":"bayesian-convolutional-neural-networks-with","repo_url":"https://github.com/aredier/monte_carlo_dropout","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"bayesian-convolutional-neural-networks-with","repo_url":"https://github.com/raj-shah/BayesianCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"bayesian-convolutional-neural-networks-with","repo_url":"https://github.com/samtuleen/skin-cancer-image-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"small-data","task_name":"Small Data Image Classification"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1506.02158","atlas_url":"https://app.syntology.ai/?focus=1506.02158","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":"1506.02158"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1506.02158\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1506.02158"},"call":"get_concepts_for_paper(arxiv_id=\"1506.02158\")"}],"by_repo":[{"repo":"aredier/monte_carlo_dropout","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"raj-shah/BayesianCNN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"samtuleen/skin-cancer-image-classification","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":"cd5dae7596d10003cdf5a40e0ead7cb73254910a9443417dae1bcd8018ad3474","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}