{"type":"ScholarlyArticle","title":"Deep Learning with Requirements in the Real World","authors":[{"name":"Mihaela C. Stoian","slug":"mihaela-c-stoian","given":"Mihaela C.","family":"Stoian","affiliation":"University of Oxford"}],"abstract":"Deep learning models have repeatedly shown their strengths in various application domains. However, their predictions often struggle to meet background knowledge requirements, which is a crucial condition for safety-critical systems. My research focuses on integrating requirements into neural networks to guide the learning process and ultimately produce outputs that ensure the requirements' satisfaction. Here, I will discuss my proposed methods in the context of two real-world applications: tabular data generation and autonomous driving.","doi":"10.24963/ijcai.2024/969","url":"https://ijcai.org/proceedings/2024/969","pdf":"https://ijcai.org/proceedings/2024/0969.pdf","markdown":"https://ijcai.org/proceedings/2024/969.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/969","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Doctoral Consortium","track":"Doctoral Consortium","number":969,"pages":{"first":8508,"last":8509},"keywords":["DC: Multidisciplinary Topics and Applications","DC: Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Ahmed et al., 2022] K. Ahmed, S. Teso, K. Chang, G. V. den Broeck, and A. Vergari. Semantic probabilistic layers for neuro-symbolic learning. In Proc. of NeurIPS, 2022.","title":"Semantic probabilistic layers for neuro-symbolic learning","authors":"K Ahmed, S Teso, K Chang, G V Broeck, A Vergari","year":"2022","venue":"Proc. of NeurIPS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Badreddine et al., 2022] S. Badreddine, A. d'Avila Garcez, L. Serafini, and M. Spranger. Logic tensor networks. Artif. Intell., 303, 2022.","title":"Logic tensor networks","authors":"S Badreddine, A Garcez, L Serafini, M Spranger","year":"2022","venue":"Artif. Intell","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Diligenti et al., 2012] M. Diligenti, M. Gori, M. Maggini, and L. Rigutini. Bridging logic and kernel machines. Mach. Learn., 86, 2012.","title":"Bridging logic and kernel machines","authors":"M Diligenti, M Gori, M Maggini, L Rigutini","year":"2012","venue":"Mach. Learn","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Giannini et al., 2023] F. Giannini, M. Diligenti, M. Mag- gini, M. Gori, and G. Marra. T-norms driven loss functions for machine learning. Appl. Intell., 53, 2023.","title":"T-norms driven loss functions for machine learning","authors":"F Giannini, M Diligenti, M Maggini, M Gori, G Marra","year":"2023","venue":"Appl. Intell","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Giunchiglia and Lukasiewicz, 2021] E. Giunchiglia and T. Lukasiewicz. Multi-label classification neural networks with hard logical constraints. JAIR, 72, 2021.","title":"Multi-label classification neural networks with hard logical constraints","authors":"E Giunchiglia, T Lukasiewicz","year":"2021","venue":"JAIR","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Giunchiglia et al., 2023] E. Giunchiglia, M. C. Stoian, S. Khan, F. Cuzzolin, and T. Lukasiewicz. ROAD-R: The autonomous driving dataset for learning with require- ments. Mach. Learn., 2023.","title":"ROAD-R: The autonomous driving dataset for learning with requirements","authors":"E Giunchiglia, M C Stoian, S Khan, F Cuzzolin, T Lukasiewicz","year":"2023","venue":"Mach. Learn","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hoernle et al., 2022] N. Hoernle, R. Karampatsis, V. Belle, and K. Gal. MultiplexNet: Towards fully satisfied logical constraints in neural networks. In Proc. of AAAI, 2022.","title":"MultiplexNet: Towards fully satisfied logical constraints in neural networks","authors":"N Hoernle, R Karampatsis, V Belle, K Gal","year":"2022","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Stoian et al., 2023] M. C. Stoian, E. Giunchiglia, and T. Lukasiewicz. Exploiting t-norms for deep learning in autonomous driving. In Proc. of International Workshop on Neural-Symbolic Learning and Reasoning, 2023.","title":"Exploiting t-norms for deep learning in autonomous driving","authors":"M C Stoian, E Giunchiglia, T Lukasiewicz","year":"2023","venue":"Proc. of International Workshop on Neural-Symbolic Learning and Reasoning","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Stoian et al., 2024] M. C. Stoian, S. Dyrmishi, M. Cordy, T. Lukasiewicz, and E. Giunchiglia. How realistic is your synthetic data? Constraining deep generative models for tabular data. In Proc. of ICLR, 2024.","title":"How realistic is your synthetic data? Constraining deep generative models for tabular data","authors":"M C Stoian, S Dyrmishi, M Cordy, T Lukasiewicz, E Giunchiglia","year":"2024","venue":"Proc. of ICLR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Xu et al., 2018] J. Xu, Z. Zhang, T. Friedman, Y. Liang, and G. V. den Broeck. A semantic loss function for deep learn- ing with symbolic knowledge. In Proc. of ICML, 2018.","title":"A semantic loss function for deep learning with symbolic knowledge","authors":"J Xu, Z Zhang, T Friedman, Y Liang, G V Broeck","year":"2018","venue":"Proc. of ICML","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}