{"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/deep-learning-using-linear-support-vector","title":"Deep Learning using Linear Support Vector Machines","arxiv_id":"1306.0239","date":"2013-06-02","proceeding":null,"authors":["Yichuan Tang"],"abstract":"Recently, fully-connected and convolutional neural networks have been trained\nto achieve state-of-the-art performance on a wide variety of tasks such as\nspeech recognition, image classification, natural language processing, and\nbioinformatics. For classification tasks, most of these \"deep learning\" models\nemploy the softmax activation function for prediction and minimize\ncross-entropy loss. In this paper, we demonstrate a small but consistent\nadvantage of replacing the softmax layer with a linear support vector machine.\nLearning minimizes a margin-based loss instead of the cross-entropy loss. While\nthere have been various combinations of neural nets and SVMs in prior art, our\nresults using L2-SVMs show that by simply replacing softmax with linear SVMs\ngives significant gains on popular deep learning datasets MNIST, CIFAR-10, and\nthe ICML 2013 Representation Learning Workshop's face expression recognition\nchallenge.","url_abs":"http://arxiv.org/abs/1306.0239v4","url_pdf":"http://arxiv.org/pdf/1306.0239v4.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":"deep-learning-using-linear-support-vector","repo_url":"https://github.com/AFAgarap/cnn-svm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"deep-learning-using-linear-support-vector","repo_url":"https://github.com/AFAgarap/malware-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"deep-learning-using-linear-support-vector","repo_url":"https://github.com/hgupta01/svm_classification_keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1306.0239","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}