{"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/build-a-deep-neural-network-model-using-cpus","title":"Build a Deep Neural Network model using CPUs Builds a feed-forward multilayer artificial neural network on an H2OFrame","arxiv_id":null,"date":"2015-09-01","proceeding":"H2O.ai, Inc. 2015 9","authors":["Anisha Arora","Arno Candel","Jessica Lanford","Erin LeDell","Viraj Parmar"],"abstract":"H2O is fast, scalable, open-source machine learning and deep learning for\r\nsmarter applications. With H2O, enterprises like PayPal, Nielsen Catalina,\r\nCisco, and others can use all their data without sampling to get accurate\r\npredictions faster. Advanced algorithms such as deep learning, boosting, and\r\nbagging ensembles are built-in to help application designers create smarter\r\napplications through elegant APIs. Some of our initial customers have built\r\npowerful domain-speci\fc predictive engines for recommendations, customer\r\nchurn, propensity to buy, dynamic pricing, and fraud detection for the insurance,\r\nhealthcare, telecommunications, ad tech, retail, and payment systems industries.\r\nUsing in-memory compression, H2O handles billions of data rows in-memory,\r\neven with a small cluster. To make it easier for non-engineers to create complete\r\nanalytic work\r\nows, H2O's platform includes interfaces for R, Python, Scala,\r\nJava, JSON, and Co\u000beeScript/JavaScript, as well as a built-in web interface,\r\nFlow. H2O is designed to run in standalone mode, on Hadoop, or within a\r\nSpark Cluster, and typically deploys within minutes.\r\nH2O includes many common machine learning algorithms, such as generalized\r\nlinear modeling (linear regression, logistic regression, etc.), Na\u0010ve Bayes, principal\r\ncomponents analysis, k-means clustering, and others. H2O also implements\r\nbest-in-class algorithms at scale, such as distributed random forest, gradient\r\nboosting and deep learning. Customers can build thousands of models and\r\ncompare the results to get the best predictions.\r\nH2O is nurturing a grassroots movement of physicists, mathematicians, and\r\ncomputer scientists to herald the new wave of discovery with data science by\r\ncollaborating closely with academic researchers and industrial data scientists.\r\nStanford university giants Stephen Boyd, Trevor Hastie, Rob Tibshirani advise\r\nthe H2O team on building scalable machine learning algorithms. With hundreds\r\nof meetups over the past three years, H2O has become a word-of-mouth\r\nphenomenon, growing amongst the data community by a hundred-fold, and\r\nis now used by 30,000+ users and is deployed using R, Python, Hadoop, and\r\nSpark in 2000+ corporations.","url_abs":"https://www.rdocumentation.org/packages/h2o/versions/3.10.5.3/topics/h2o.deeplearning","url_pdf":"http://h2o-release.s3.amazonaws.com/h2o/master/3195/docs-website/h2o-docs/booklets/DeepLearning_Vignette.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":"build-a-deep-neural-network-model-using-cpus","repo_url":"https://github.com/h2oai/h2o-3","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"fraud-detection","task_name":"Fraud Detection"}],"methods":[{"method_slug":"h2o-dl","method_name":"H2O DL"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}