{"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/feature-space-saturation-during-training","title":"Feature Space Saturation during Training","arxiv_id":"2006.08679","date":"2020-06-15","proceeding":null,"authors":["Mats L. Richter","Justin Shenk","Wolf Byttner","Anders Arpteg","Mikael Huss"],"abstract":"We propose layer saturation - a simple, online-computable method for analyzing the information processing in neural networks. First, we show that a layer's output can be restricted to the eigenspace of its variance matrix without performance loss. We propose a computationally lightweight method for approximating the variance matrix during training. From the dimension of its lossless eigenspace we derive layer saturation - the ratio between the eigenspace dimension and layer width. We show that saturation seems to indicate which layers contribute to network performance. We demonstrate how to alter layer saturation in a neural network by changing network depth, filter sizes and input resolution. Furthermore, we show that well-chosen input resolution increases network performance by distributing the inference process more evenly across the network.","url_abs":"https://arxiv.org/abs/2006.08679v5","url_pdf":"https://arxiv.org/pdf/2006.08679v5.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":"feature-space-saturation-during-training","repo_url":"https://github.com/delve-team/delve","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"feature-space-saturation-during-training","repo_url":"https://github.com/mlrichter/phd-lab","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}