{"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/bayesian-neural-networks","title":"Bayesian Neural Networks","arxiv_id":"1801.07710","date":"2018-01-23","proceeding":null,"authors":["Vikram Mullachery","Aniruddh Khera","Amir Husain"],"abstract":"This paper describes and discusses Bayesian Neural Network (BNN). The paper\nshowcases a few different applications of them for classification and\nregression problems. BNNs are comprised of a Probabilistic Model and a Neural\nNetwork. The intent of such a design is to combine the strengths of Neural\nNetworks and Stochastic modeling. Neural Networks exhibit continuous function\napproximator capabilities. Stochastic models allow direct specification of a\nmodel with known interaction between parameters to generate data. During the\nprediction phase, stochastic models generate a complete posterior distribution\nand produce probabilistic guarantees on the predictions. Thus BNNs are a unique\ncombination of neural network and stochastic models with the stochastic model\nforming the core of this integration. BNNs can then produce probabilistic\nguarantees on it's predictions and also generate the distribution of parameters\nthat it has learnt from the observations. That means, in the parameter space,\none can deduce the nature and shape of the neural network's learnt parameters.\nThese two characteristics makes them highly attractive to theoreticians as well\nas practitioners. Recently there has been a lot of activity in this area, with\nthe advent of numerous probabilistic programming libraries such as: PyMC3,\nEdward, Stan etc. Further this area is rapidly gaining ground as a standard\nmachine learning approach for numerous problems","url_abs":"http://arxiv.org/abs/1801.07710v2","url_pdf":"http://arxiv.org/pdf/1801.07710v2.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":"bayesian-neural-networks","repo_url":"https://github.com/mullachv/MLExp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"probabilistic-programming","task_name":"Probabilistic Programming"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}