{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-neural-network-initialization-with","title":"Deep neural network initialization with decision trees","arxiv_id":"1707.00784","date":"2017-07-03","proceeding":null,"authors":["K. D. Humbird","J. L. Peterson","R. G. McClarren"],"abstract":"In this work a novel, automated process for constructing and initializing\ndeep feed-forward neural networks based on decision trees is presented. The\nproposed algorithm maps a collection of decision trees trained on the data into\na collection of initialized neural networks, with the structures of the\nnetworks determined by the structures of the trees. The tree-informed\ninitialization acts as a warm-start to the neural network training process,\nresulting in efficiently trained, accurate networks. These models, referred to\nas \"deep jointly-informed neural networks\" (DJINN), demonstrate high predictive\nperformance for a variety of regression and classification datasets, and\ndisplay comparable performance to Bayesian hyper-parameter optimization at a\nlower computational cost. By combining the user-friendly features of decision\ntree models with the flexibility and scalability of deep neural networks, DJINN\nis an attractive algorithm for training predictive models on a wide range of\ncomplex datasets.","url_abs":"http://arxiv.org/abs/1707.00784v3","url_pdf":"http://arxiv.org/pdf/1707.00784v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-neural-network-initialization-with","repo_url":"https://github.com/LLNL/DJINN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}