{"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/formal-verification-of-piece-wise-linear-feed","title":"Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks","arxiv_id":"1705.01320","date":"2017-05-03","proceeding":null,"authors":["Ruediger Ehlers"],"abstract":"We present an approach for the verification of feed-forward neural networks\nin which all nodes have a piece-wise linear activation function. Such networks\nare often used in deep learning and have been shown to be hard to verify for\nmodern satisfiability modulo theory (SMT) and integer linear programming (ILP)\nsolvers.\n  The starting point of our approach is the addition of a global linear\napproximation of the overall network behavior to the verification problem that\nhelps with SMT-like reasoning over the network behavior. We present a\nspecialized verification algorithm that employs this approximation in a search\nprocess in which it infers additional node phases for the non-linear nodes in\nthe network from partial node phase assignments, similar to unit propagation in\nclassical SAT solving. We also show how to infer additional conflict clauses\nand safe node fixtures from the results of the analysis steps performed during\nthe search. The resulting approach is evaluated on collision avoidance and\nhandwritten digit recognition case studies.","url_abs":"http://arxiv.org/abs/1705.01320v3","url_pdf":"http://arxiv.org/pdf/1705.01320v3.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":"formal-verification-of-piece-wise-linear-feed","repo_url":"https://github.com/progirep/planet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"collision-avoidance","task_name":"Collision Avoidance"},{"task_slug":"handwritten-digit-recognition","task_name":"Handwritten Digit Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.01320","atlas_url":"https://app.syntology.ai/?focus=1705.01320","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":"1705.01320"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1705.01320\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1705.01320"},"call":"get_concepts_for_paper(arxiv_id=\"1705.01320\")"}],"by_repo":[{"repo":"progirep/planet","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":"1ee74e56e50b1b28257073e1f0c28055c0f8c2ed6d3289467a5d7fe7715d0d21","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}