{"type":"ScholarlyArticle","title":"Deep Neural Decision Forests","authors":[{"name":"Peter Kontschieder","slug":"peter-kontschieder","given":"Peter","family":"Kontschieder","affiliation":""},{"name":"Madalina Fiterau","slug":"madalina-fiterau","given":"Madalina","family":"Fiterau","affiliation":""},{"name":"Antonio Criminisi","slug":"antonio-criminisi","given":"Antonio","family":"Criminisi","affiliation":""},{"name":"Samuel Rota Bulò","slug":"samuel-rota-bulo","given":"Samuel Rota","family":"Bulò","affiliation":""}],"abstract":"We present a novel approach to enrich classification trees with the representation learning ability of deep (neural) networks within an end-to-end trainable architecture. We combine these two worlds via a stochastic and differentiable decision tree model, which steers the formation of latent representations within the hidden layers of a deep network. The proposed model differs from conventional deep networks in that a decision forest provides the final predictions and it differs from conventional decision forests by introducing a principled, joint and global optimization of split and leaf node parameters. Our approach compares favourably to other state-of-the-art deep models on a large-scale image classification task like ImageNet.","doi":null,"url":"https://ijcai.org/proceedings/2016/628","pdf":"https://ijcai.org/proceedings/2016/0628.pdf","markdown":"https://ijcai.org/proceedings/2016/628.md","bibtex":"https://ijcai.org/proceedings/2016/bibtex/628","volume":{"slug":"2016","title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2016","url":"https://ijcai.org/proceedings/2016/","year":2016,"location":"New York, NY, USA","dates":"9–15 July 2016","editors":"Subbarao Kambhampati","isbn":"978-1-57735-770-4; 978-1-57735-771-1","publisher":"AAAI Press / International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":628,"pages":{"first":4190,"last":4193},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}