{"type":"ScholarlyArticle","title":"Explainable Deep Neural Networks for Multivariate Time Series Predictions","authors":[{"name":"Roy Assaf","slug":"roy-assaf","given":"Roy","family":"Assaf","affiliation":"IBM Research , Zurich"},{"name":"Anika Schumann","slug":"anika-schumann","given":"Anika","family":"Schumann","affiliation":"IBM Research , Zurich"}],"abstract":"We demonstrate that CNN deep neural networks can not only be used for making predictions based on multivariate time series data, but also for explaining these predictions. \r\nThis is important for a number of applications where predictions are the basis for decisions and actions. Hence, confidence in the prediction result is crucial. \r\nWe design a two stage convolutional neural network architecture which uses particular kernel sizes.\r\nThis allows us to utilise gradient based techniques for generating saliency maps for both the time dimension and the features.\r\nThese are then used for explaining which features during which time interval are responsible for a given prediction, as well as explaining during which time intervals was the joint contribution of all features most important for that prediction. \r\nWe demonstrate our approach for predicting the average energy production of photovoltaic power plants and for explaining these predictions.","doi":"10.24963/ijcai.2019/932","url":"https://ijcai.org/proceedings/2019/932","pdf":"https://ijcai.org/proceedings/2019/0932.pdf","markdown":"https://ijcai.org/proceedings/2019/932.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/932","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Demos","track":"Demos","number":932,"pages":{"first":6488,"last":6490},"keywords":["Applications: Energy","AI: Knowledge Representation and Reasoning","AI: Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Adebayo et al., 2018] Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, and Been Kim. Sanity checks for saliency maps. In Ad- vances in Neural Information Processing Systems, pages 9505-9515, 2018.","title":"Sanity checks for saliency maps","authors":"Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, Been Kim","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ceci et al., 2017] Michelangelo Ceci, Roberto Corizzo, Fabio Fumarola, Donato Malerba, and Aleksandra Rashkovska. Predictive modeling of pv energy production: How to set up the learning task for a better prediction? IEEE Transactions on Industrial Informatics, 13(3):956- 966, 2017.","title":"Predictive modeling of pv energy production: How to set up the learning task for a better prediction","authors":"Ceci","year":"2017","venue":"IEEE Transactions on Industrial Informatics","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Fawaz et al., 2018] Hassan Ismail Fawaz, Germain Forestier, Jonathan Weber, Lhassane Idoumghar, and Pierre-Alain Muller. Deep learning for time series classification: a review. arXiv preprint arXiv:1809.04356, 2018.","title":"Deep learning for time series classification: a review","authors":"Hassan Ismail Fawaz, Germain Forestier, Jonathan Weber, Lhassane Idoumghar, Pierre-Alain Muller","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Gilpin et al., 2018] Leilani H Gilpin, David Bau, Ben Z Yuan, Ayesha Bajwa, Michael Specter, and Lalana Ka- gal. Explaining explanations: An approach to evaluat- ing interpretability of machine learning. arXiv preprint arXiv:1806.00069, 2018.","title":"Explaining explanations: An approach to evaluating interpretability of machine learning","authors":"David Leilani H Gilpin, Bau, Ayesha Ben Z Yuan, Michael Bajwa, Lalana Specter, Kagal","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[LeCun et al., 1995] Yann LeCun, Yoshua Bengio, et al. Convolutional networks for images, speech, and time se- ries. The handbook of brain theory and neural networks, 3361(10):1995, 1995.","title":"Convolutional networks for images, speech, and time series","authors":"Yann Lecun, Yoshua Bengio","year":"1995","venue":"The handbook of brain theory and neural networks","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Lin et al., 2013] Min Lin, Qiang Chen, and Shuicheng Yan. Network in network. arXiv preprint arXiv:1312.4400, 2013.","title":"Network in network","authors":"Lin","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Selvaraju et al., 2017] Ramprasaath R Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. Grad-cam: Visual explanations from deep networks via gradient-based localization. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 618-626. IEEE, 2017.","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","authors":"Michael Ramprasaath R Selvaraju, Abhishek Cogswell, Ramakrishna Das, Devi Vedantam, Dhruv Parikh, Batra","year":"2017","venue":"IEEE International Conference on Computer Vision (ICCV)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Szegedy et al., 2015] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabi- novich. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1-9, 2015.","title":"Going deeper with convolutions","authors":"Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich","year":"2015","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Xing et al., 2010] Zhengzheng Xing, Jian Pei, and Eamonn Keogh. A brief survey on sequence classification. ACM Sigkdd Explorations Newsletter, 12(1):40-48, 2010.","title":"A brief survey on sequence classification","authors":"Xing","year":"2010","venue":"ACM Sigkdd Explorations Newsletter","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Zheng et al., 2014] Yi Zheng, Qi Liu, Enhong Chen, Yong Ge, and J Leon Zhao. Time series classification using multi-channels deep convolutional neural networks. In In- ternational Conference on Web-Age Information Manage- ment, pages 298-310. Springer, 2014.","title":"Time series classification using multi-channels deep convolutional neural networks","authors":"Yi Zheng, Qi Liu, Enhong Chen, Yong Ge, Leon Zhao","year":"2014","venue":"International Conference on Web-Age Information Management","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Zheng et al., 2016] Yi Zheng, Qi Liu, Enhong Chen, Yong Ge, and J Leon Zhao. Exploiting multi-channels deep convolutional neural networks for multivariate time series classification. Frontiers of Computer Science, 10(1):96- 112, 2016.","title":"Exploiting multi-channels deep convolutional neural networks for multivariate time series classification","authors":"Yi Zheng, Qi Liu, Enhong Chen, Yong Ge, Leon Zhao","year":"2016","venue":"Frontiers of Computer Science","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}