{"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/how-much-chemistry-does-a-deep-neural-network","title":"How Much Chemistry Does a Deep Neural Network Need to Know to Make Accurate Predictions?","arxiv_id":"1710.02238","date":"2017-10-05","proceeding":null,"authors":["Garrett B. Goh","Charles Siegel","Abhinav Vishnu","Nathan O. Hodas","Nathan Baker"],"abstract":"The meteoric rise of deep learning models in computer vision research, having\nachieved human-level accuracy in image recognition tasks is firm evidence of\nthe impact of representation learning of deep neural networks. In the chemistry\ndomain, recent advances have also led to the development of similar CNN models,\nsuch as Chemception, that is trained to predict chemical properties using\nimages of molecular drawings. In this work, we investigate the effects of\nsystematically removing and adding localized domain-specific information to the\nimage channels of the training data. By augmenting images with only 3\nadditional basic information, and without introducing any architectural\nchanges, we demonstrate that an augmented Chemception (AugChemception)\noutperforms the original model in the prediction of toxicity, activity, and\nsolvation free energy. Then, by altering the information content in the images,\nand examining the resulting model's performance, we also identify two distinct\nlearning patterns in predicting toxicity/activity as compared to solvation free\nenergy. These patterns suggest that Chemception is learning about its tasks in\nthe manner that is consistent with established knowledge. Thus, our work\ndemonstrates that advanced chemical knowledge is not a pre-requisite for deep\nlearning models to accurately predict complex chemical properties.","url_abs":"http://arxiv.org/abs/1710.02238v2","url_pdf":"http://arxiv.org/pdf/1710.02238v2.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":"how-much-chemistry-does-a-deep-neural-network","repo_url":"https://github.com/Abdulk084/Chemception","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"how-much-chemistry-does-a-deep-neural-network","repo_url":"https://github.com/Bunseki2/DeepL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"Abdulk084/Chemception","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Bunseki2/DeepL","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":"0626b565675b940ef3ddd0a92810a348bfddbfff62d4696c93fa57d14aa930f8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}