{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T01:18:48Z","timestamp":1751937528110,"version":"3.28.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1109\/ijcnn.2019.8851954","type":"proceedings-article","created":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T03:44:32Z","timestamp":1569901472000},"page":"1-8","source":"Crossref","is-referenced-by-count":6,"title":["Response Characterization for Auditing Cell Dynamics in Long Short-term Memory Networks"],"prefix":"10.1109","author":[{"given":"Ramin","family":"Hasani","sequence":"first","affiliation":[]},{"given":"Alexander","family":"Amini","sequence":"additional","affiliation":[]},{"given":"Mathias","family":"Lechner","sequence":"additional","affiliation":[]},{"given":"Felix","family":"Naser","sequence":"additional","affiliation":[]},{"given":"Radu","family":"Grosu","sequence":"additional","affiliation":[]},{"given":"Daniela","family":"Rus","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(09)80007-5"},{"key":"ref38","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref33","article-title":"Compositional attention networks for machine reasoning","author":"hudson","year":"2018","journal-title":"arXiv preprint arXiv 1803 03067"},{"key":"ref32","first-page":"1693","article-title":"Teaching machines to read and comprehend","author":"hermann","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(99)00114-9"},{"key":"ref36","first-page":"455","article-title":"Observability of neural network behavior","author":"garzon","year":"1994","journal-title":"Advances in neural information processing systems"},{"key":"ref35","first-page":"1","article-title":"Recurrent neural networks: Identification and other system theoretic properties","volume":"3","author":"albertini","year":"1995","journal-title":"Neural Network Systems Techniques and Applications"},{"key":"ref34","first-page":"599","article-title":"Uniqueness of weights for recurrent nets","volume":"79","author":"albertini","year":"1994","journal-title":"Mathematical Research"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2744158"},{"key":"ref40","volume":"6","author":"sontag","year":"2013","journal-title":"Mathematical Control Theory Deterministic Finite Dimensional Systems"},{"journal-title":"Signals and Systems","year":"1983","author":"oppenheim","key":"ref11"},{"key":"ref12","first-page":"1","article-title":"Visualizing higher-layer features of a deep network","volume":"1341","author":"erhan","year":"2009","journal-title":"University of Montreal"},{"key":"ref13","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref14","article-title":"Understanding neural networks through deep visualization","author":"yosinski","year":"2015","journal-title":"arXiv preprint arXiv 1506 06579"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2744683"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00010"},{"key":"ref17","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"simonyan","year":"2013","journal-title":"arXiv preprint arXiv 1312 6034"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"key":"ref19","article-title":"Patternnet and patternlrp–improving the interpretability of neural networks","author":"kindermans","year":"2017","journal-title":"arXiv preprint arXiv 1705 05598"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2804"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref27","article-title":"Re-purposing compact neuronal circuit policies to govern reinforcement learning tasks","author":"hasani","year":"2018","journal-title":"arXiv preprint arXiv 1809 04423"},{"key":"ref3","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref6","article-title":"Visualizing and understanding recurrent networks","author":"karpathy","year":"2015","journal-title":"arXiv preprint arXiv 1506 03857"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/COLI_a_00300"},{"key":"ref5","first-page":"305","article-title":"ALVINN: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1989","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv preprint arXiv 1412 3555"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref2","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016","journal-title":"arXiv preprint arXiv 1604 07316"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793579"},{"key":"ref20","article-title":"Axiomatic attribution for deep networks","author":"sundararajan","year":"2017","journal-title":"arXiv preprint arXiv 1703 01210"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/0022-2836(88)90564-5"},{"key":"ref22","article-title":"Pixelvae: A latent variable model for natural images","author":"gulrajani","year":"2016","journal-title":"arXiv preprint arXiv 1611 05013"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/34.667885"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594386"},{"article-title":"MNIST handwritten digit database","year":"2010","author":"lecun","key":"ref41"},{"key":"ref23","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"journal-title":"Atmospheric Carbon Dioxide Record","year":"0","author":"keeling","key":"ref44"},{"key":"ref26","article-title":"Opening the black box of deep neural networks via information","author":"shwartz-ziv","year":"2017","journal-title":"arXiv preprint arXiv 1703 06870"},{"journal-title":"Yahoo Finance Website S&P 500 Stock","year":"0","key":"ref43"},{"key":"ref25","article-title":"Understanding black-box predictions via influence functions","author":"koh","year":"2017","journal-title":"arXiv preprint arXiv 1703 04529"}],"event":{"name":"2019 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2019,7,14]]},"location":"Budapest, Hungary","end":{"date-parts":[[2019,7,19]]}},"container-title":["2019 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8840768\/8851681\/08851954.pdf?arnumber=8851954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:51:00Z","timestamp":1658094660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8851954\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2019.8851954","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}