{"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/layer-wise-relevance-propagation-for-neural","title":"Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers","arxiv_id":"1604.00825","date":"2016-04-04","proceeding":null,"authors":["Alexander Binder","Grégoire Montavon","Sebastian Bach","Klaus-Robert Müller","Wojciech Samek"],"abstract":"Layer-wise relevance propagation is a framework which allows to decompose the\nprediction of a deep neural network computed over a sample, e.g. an image, down\nto relevance scores for the single input dimensions of the sample such as\nsubpixels of an image. While this approach can be applied directly to\ngeneralized linear mappings, product type non-linearities are not covered. This\npaper proposes an approach to extend layer-wise relevance propagation to neural\nnetworks with local renormalization layers, which is a very common product-type\nnon-linearity in convolutional neural networks. We evaluate the proposed method\nfor local renormalization layers on the CIFAR-10, Imagenet and MIT Places\ndatasets.","url_abs":"http://arxiv.org/abs/1604.00825v1","url_pdf":"http://arxiv.org/pdf/1604.00825v1.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":"layer-wise-relevance-propagation-for-neural","repo_url":"https://github.com/tomsawyerhu/lrp4rag","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.00825","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}