{"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/re-training-binary-neural-networks-using-the","title":"[Re] Training Binary Neural Networks using the Bayesian Learning Rule","arxiv_id":null,"date":"2021-01-31","proceeding":"RC 2020","authors":["Prateek Garg","Lakshya Singhal","Ashish Sardana"],"abstract":"Scope of Reproducibility\n\nWe try to verify the performance of our re-implementation of the BayesBiNN optimizer on various classification and regression benchmarks. We also implemented the STE optimizer which was the central baseline model used in the paper. Finally, we tried to evaluate the results of BayesBiNN on the continual learning benchmark to get a better insight.\n\nMethodology\n\nWe developed our separate code-base, consisting of an end-to-end trainer with a Keraslike interface, for the reproduction which includes the implementation of the BayesBiNN and STE optimizer. We did refer to the authorʼs code open-sourced on GitHub to get some insights about the hyperparameters and other doubts that emerged during code development.\n\nResults\n\nWe reproduced the accuracy of the BayesBiNN optimizer within less than 0.5% of the originally reported value, which upholds the conclusion that it performs nearly as well as its full precision counterpart in classification tasks. When we tried this in a semantic segmentation context, we found that the results were very underwhelming and in contrast with the seemingly good results by the STE optimizer even with much hyperparameter tuning. We can conclude that, like other Bayesian methods, it is difficult to train BayesBiNN on more complex tasks.\n\nWhat was easy\n\nAfter we worked out the mathematics behind the BayesBiNN approach, we developed a pseudo-code for the optimization process which along with references from the authorʼs code, helped us a lot in our reproduction study.\n\nWhat was difficult\n\nSome of the hyperparameters were not mentioned by the authors in their paper so it was difficult to approximate the values of those parameters. The lack of resources was the next big difficulty that we faced.\n\nCommunication with original authors\n\nWe had a very fruitful conversation with the authors, which helped us in better understanding the BayesBiNN approach and its extension to the segmentation domain. The detailed pointers are given at the end of this report.","url_abs":"http://rescience.github.io/bibliography/Garg_2021.html","url_pdf":"https://zenodo.org/record/4833681/files/article.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":"re-training-binary-neural-networks-using-the","repo_url":"https://github.com/prateekstark/training-binary-neural-network","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"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}