{"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/recurrent-neural-networks-with-limited","title":"Recurrent Neural Networks With Limited Numerical Precision","arxiv_id":"1611.07065","date":"2016-11-21","proceeding":null,"authors":["Joachim Ott","Zhouhan Lin","Ying Zhang","Shih-Chii Liu","Yoshua Bengio"],"abstract":"Recurrent Neural Networks (RNNs) produce state-of-art performance on many\nmachine learning tasks but their demand on resources in terms of memory and\ncomputational power are often high. Therefore, there is a great interest in\noptimizing the computations performed with these models especially when\nconsidering development of specialized low-power hardware for deep networks.\nOne way of reducing the computational needs is to limit the numerical precision\nof the network weights and biases, and this will be addressed for the case of\nRNNs. We present results from the use of different stochastic and deterministic\nreduced precision training methods applied to two major RNN types, which are\nthen tested on three datasets. The results show that the stochastic and\ndeterministic ternarization, pow2- ternarization, and exponential quantization\nmethods gave rise to low-precision RNNs that produce similar and even higher\naccuracy on certain datasets, therefore providing a path towards training more\nefficient implementations of RNNs in specialized hardware.","url_abs":"http://arxiv.org/abs/1611.07065v2","url_pdf":"http://arxiv.org/pdf/1611.07065v2.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":"recurrent-neural-networks-with-limited","repo_url":"https://github.com/ottj/QuantizedRNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"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}