{"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/forward-thinking-building-deep-random-forests","title":"Forward Thinking: Building Deep Random Forests","arxiv_id":"1705.07366","date":"2017-05-20","proceeding":null,"authors":["Kevin Miller","Chris Hettinger","Jeffrey Humpherys","Tyler Jarvis","David Kartchner"],"abstract":"The success of deep neural networks has inspired many to wonder whether other\nlearners could benefit from deep, layered architectures. We present a general\nframework called forward thinking for deep learning that generalizes the\narchitectural flexibility and sophistication of deep neural networks while also\nallowing for (i) different types of learning functions in the network, other\nthan neurons, and (ii) the ability to adaptively deepen the network as needed\nto improve results. This is done by training one layer at a time, and once a\nlayer is trained, the input data are mapped forward through the layer to create\na new learning problem. The process is then repeated, transforming the data\nthrough multiple layers, one at a time, rendering a new dataset, which is\nexpected to be better behaved, and on which a final output layer can achieve\ngood performance. In the case where the neurons of deep neural nets are\nreplaced with decision trees, we call the result a Forward Thinking Deep Random\nForest (FTDRF). We demonstrate a proof of concept by applying FTDRF on the\nMNIST dataset. We also provide a general mathematical formulation that allows\nfor other types of deep learning problems to be considered.","url_abs":"http://arxiv.org/abs/1705.07366v1","url_pdf":"http://arxiv.org/pdf/1705.07366v1.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":"forward-thinking-building-deep-random-forests","repo_url":"https://github.com/tkchris93/ForwardThinking","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"forward-thinking-building-deep-random-forests","repo_url":"https://github.com/malaschitz/randomForest","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.07366","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}