{"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/compressed-learning-a-deep-neural-network","title":"Compressed Learning: A Deep Neural Network Approach","arxiv_id":"1610.09615","date":"2016-10-30","proceeding":null,"authors":["Amir Adler","Michael Elad","Michael Zibulevsky"],"abstract":"Compressed Learning (CL) is a joint signal processing and machine learning\nframework for inference from a signal, using a small number of measurements\nobtained by linear projections of the signal. In this paper we present an\nend-to-end deep learning approach for CL, in which a network composed of\nfully-connected layers followed by convolutional layers perform the linear\nsensing and non-linear inference stages. During the training phase, the sensing\nmatrix and the non-linear inference operator are jointly optimized, and the\nproposed approach outperforms state-of-the-art for the task of image\nclassification. For example, at a sensing rate of 1% (only 8 measurements of 28\nX 28 pixels images), the classification error for the MNIST handwritten digits\ndataset is 6.46% compared to 41.06% with state-of-the-art.","url_abs":"http://arxiv.org/abs/1610.09615v1","url_pdf":"http://arxiv.org/pdf/1610.09615v1.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":"compressed-learning-a-deep-neural-network","repo_url":"https://github.com/viebboy/MultilinearCompressiveLearningFramework","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"compressed-learning-a-deep-neural-network","repo_url":"https://github.com/viebboy/MultilinearCompressiveLearningWithPrior","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}