{"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/an-empirical-investigation-of-catastrophic","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","arxiv_id":"1312.6211","date":"2013-12-21","proceeding":null,"authors":["Ian J. Goodfellow","Mehdi Mirza","Da Xiao","Aaron Courville","Yoshua Bengio"],"abstract":"Catastrophic forgetting is a problem faced by many machine learning models\nand algorithms. When trained on one task, then trained on a second task, many\nmachine learning models \"forget\" how to perform the first task. This is widely\nbelieved to be a serious problem for neural networks. Here, we investigate the\nextent to which the catastrophic forgetting problem occurs for modern neural\nnetworks, comparing both established and recent gradient-based training\nalgorithms and activation functions. We also examine the effect of the\nrelationship between the first task and the second task on catastrophic\nforgetting. We find that it is always best to train using the dropout\nalgorithm--the dropout algorithm is consistently best at adapting to the new\ntask, remembering the old task, and has the best tradeoff curve between these\ntwo extremes. We find that different tasks and relationships between tasks\nresult in very different rankings of activation function performance. This\nsuggests the choice of activation function should always be cross-validated.","url_abs":"http://arxiv.org/abs/1312.6211v3","url_pdf":"http://arxiv.org/pdf/1312.6211v3.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":"an-empirical-investigation-of-catastrophic","repo_url":"https://github.com/goodfeli/forgetting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[{"slug":"permuted-mnist","name":"Permuted MNIST","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1312.6211","atlas_url":"https://app.syntology.ai/?focus=1312.6211","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":"1312.6211"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1312.6211\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1312.6211"},"call":"get_concepts_for_paper(arxiv_id=\"1312.6211\")"}],"by_repo":[{"repo":"goodfeli/forgetting","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":"55bd35466ab7976c470d7a2790ee56a56515d25252b3e7463c3c64af76ba4df0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}