{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T22:32:31Z","timestamp":1777242751994,"version":"3.51.4"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,7]]},"abstract":"<jats:p>We consider the compilation of a binary neural network\u2019s decision function into tractable representations such as Ordered Binary Decision Diagrams (OBDDs) and Sentential Decision Diagrams (SDDs). Obtaining this function as an OBDD\/SDD facilitates the explanation and formal veri\ufb01cation of a neural network\u2019s behavior. First, we consider the task of verifying the robustness of a neural network, and show how we can compute the expected robustness of a neural network, given an OBDD\/SDD representation of it. Next, we consider a more ef\ufb01cient approach for compiling neural networks, based on a pseudo-polynomial time algorithm for compiling a neuron. We then provide a case study in a handwritten digits dataset, highlighting how two neural networks trained from the same dataset can have very high accuracies, yet have very different levels of robustness. Finally, in experiments, we show that it is feasible to obtain compact representations of neural networks as SDDs.<\/jats:p>","DOI":"10.24963\/kr.2020\/91","type":"proceedings-article","created":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T04:39:16Z","timestamp":1597898356000},"page":"882-892","source":"Crossref","is-referenced-by-count":27,"title":["On Tractable Representations of Binary Neural Networks"],"prefix":"10.24963","author":[{"given":"Weijia","family":"Shi","sequence":"first","affiliation":[{"name":"University of California, Los Angeles"}]},{"given":"Andy","family":"Shih","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles"}]},{"given":"Adnan","family":"Darwiche","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles"}]},{"given":"Arthur","family":"Choi","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles"}]}],"member":"10584","event":{"name":"17th International Conference on Principles of Knowledge Representation and Reasoning {KR-2020}","theme":"Artificial Intelligence","location":"Rhodes, Greece","acronym":"KR-2020","number":"17","sponsor":["Artificial Intelligence Journal","Principles of Knowledge Representation and Reasoning Inc.","Association for Logic Programming","Center for Perspicuous Computing","European Association for Artificial Intelligence","Ontopic - The Virtual Knowledge Graph Company"],"start":{"date-parts":[[2020,9,12]]},"end":{"date-parts":[[2020,9,18]]}},"container-title":["Proceedings of the Seventeenth International Conference on Principles of Knowledge Representation and Reasoning"],"original-title":[],"deposited":{"date-parts":[[2020,11,5]],"date-time":"2020-11-05T21:18:52Z","timestamp":1604611132000},"score":1,"resource":{"primary":{"URL":"https:\/\/proceedings.kr.org\/2020\/91"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/kr.2020\/91","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}