{"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-learning-with-limited-numerical","title":"Deep Learning with Limited Numerical Precision","arxiv_id":"1502.02551","date":"2015-02-09","proceeding":null,"authors":["Suyog Gupta","Ankur Agrawal","Kailash Gopalakrishnan","Pritish Narayanan"],"abstract":"Training of large-scale deep neural networks is often constrained by the\navailable computational resources. We study the effect of limited precision\ndata representation and computation on neural network training. Within the\ncontext of low-precision fixed-point computations, we observe the rounding\nscheme to play a crucial role in determining the network's behavior during\ntraining. Our results show that deep networks can be trained using only 16-bit\nwide fixed-point number representation when using stochastic rounding, and\nincur little to no degradation in the classification accuracy. We also\ndemonstrate an energy-efficient hardware accelerator that implements\nlow-precision fixed-point arithmetic with stochastic rounding.","url_abs":"http://arxiv.org/abs/1502.02551v1","url_pdf":"http://arxiv.org/pdf/1502.02551v1.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-learning-with-limited-numerical","repo_url":"https://github.com/VisionSystemsInc/nervanagpu","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"deep-learning-with-limited-numerical","repo_url":"https://github.com/yhcool14/nervanagpu","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1502.02551","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}