{"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/rethinking-the-usage-of-batch-normalization","title":"Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks","arxiv_id":"1905.05928","date":"2019-05-15","proceeding":null,"authors":["Guangyong Chen","Pengfei Chen","Yujun Shi","Chang-Yu Hsieh","Benben Liao","Shengyu Zhang"],"abstract":"In this work, we propose a novel technique to boost training efficiency of a neural network. Our work is based on an excellent idea that whitening the inputs of neural networks can achieve a fast convergence speed. Given the well-known fact that independent components must be whitened, we introduce a novel Independent-Component (IC) layer before each weight layer, whose inputs would be made more independent. However, determining independent components is a computationally intensive task. To overcome this challenge, we propose to implement an IC layer by combining two popular techniques, Batch Normalization and Dropout, in a new manner that we can rigorously prove that Dropout can quadratically reduce the mutual information and linearly reduce the correlation between any pair of neurons with respect to the dropout layer parameter $p$. As demonstrated experimentally, the IC layer consistently outperforms the baseline approaches with more stable training process, faster convergence speed and better convergence limit on CIFAR10/100 and ILSVRC2012 datasets. The implementation of our IC layer makes us rethink the common practices in the design of neural networks. For example, we should not place Batch Normalization before ReLU since the non-negative responses of ReLU will make the weight layer updated in a suboptimal way, and we can achieve better performance by combining Batch Normalization and Dropout together as an IC layer.","url_abs":"https://arxiv.org/abs/1905.05928v1","url_pdf":"https://arxiv.org/pdf/1905.05928v1.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":"rethinking-the-usage-of-batch-normalization","repo_url":"https://github.com/tae898/age-gender","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.05928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05928"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tae898/age-gender","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":7},"by_repo_kind":{"listed":{"samples":7,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2edae59f843d8ce9","entry":"accuracy","repo":"tae898/age-gender","repo_kind":"listed","path":"model/metric.py","file_url":"https://github.com/tae898/age-gender/blob/HEAD/model/metric.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2edae59f843d8ce9"}},{"code_sha256_prefix":"38ab19fce92aedaf","entry":"accuracy_mse","repo":"tae898/age-gender","repo_kind":"listed","path":"model/metric.py","file_url":"https://github.com/tae898/age-gender/blob/HEAD/model/metric.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"38ab19fce92aedaf"}},{"code_sha256_prefix":"7305e7b9b187765b","entry":"accuracy_relaxed","repo":"tae898/age-gender","repo_kind":"listed","path":"model/metric.py","file_url":"https://github.com/tae898/age-gender/blob/HEAD/model/metric.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7305e7b9b187765b"}},{"code_sha256_prefix":"bfb99459d150b0f0","entry":"cse","repo":"tae898/age-gender","repo_kind":"listed","path":"model/loss.py","file_url":"https://github.com/tae898/age-gender/blob/HEAD/model/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bfb99459d150b0f0"}},{"code_sha256_prefix":"1dc2c8c98c52e761","entry":"mse","repo":"tae898/age-gender","repo_kind":"listed","path":"model/loss.py","file_url":"https://github.com/tae898/age-gender/blob/HEAD/model/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1dc2c8c98c52e761"}},{"code_sha256_prefix":"f733c7f26bd8c1dc","entry":"nll_loss","repo":"tae898/age-gender","repo_kind":"listed","path":"model/loss.py","file_url":"https://github.com/tae898/age-gender/blob/HEAD/model/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f733c7f26bd8c1dc"}},{"code_sha256_prefix":"25e3ac309687175f","entry":"send_to_servers","repo":"tae898/age-gender","repo_kind":"listed","path":"client.py","file_url":"https://github.com/tae898/age-gender/blob/HEAD/client.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"25e3ac309687175f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}