{"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/learning-a-smooth-kernel-regularizer-for","title":"Learning a smooth kernel regularizer for convolutional neural networks","arxiv_id":"1903.01882","date":"2019-03-05","proceeding":null,"authors":["Reuben Feinman","Brenden M. Lake"],"abstract":"Modern deep neural networks require a tremendous amount of data to train,\noften needing hundreds or thousands of labeled examples to learn an effective\nrepresentation. For these networks to work with less data, more structure must\nbe built into their architectures or learned from previous experience. The\nlearned weights of convolutional neural networks (CNNs) trained on large\ndatasets for object recognition contain a substantial amount of structure.\nThese representations have parallels to simple cells in the primary visual\ncortex, where receptive fields are smooth and contain many regularities.\nIncorporating smoothness constraints over the kernel weights of modern CNN\narchitectures is a promising way to improve their sample complexity. We propose\na smooth kernel regularizer that encourages spatial correlations in convolution\nkernel weights. The correlation parameters of this regularizer are learned from\nprevious experience, yielding a method with a hierarchical Bayesian\ninterpretation. We show that our correlated regularizer can help constrain\nmodels for visual recognition, improving over an L2 regularization baseline.","url_abs":"http://arxiv.org/abs/1903.01882v1","url_pdf":"http://arxiv.org/pdf/1903.01882v1.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":"learning-a-smooth-kernel-regularizer-for","repo_url":"https://github.com/rfeinman/SK-regularization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"l2-regularization","task_name":"L2 Regularization"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}