{"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/progressive-neural-networks-for-transfer","title":"Progressive Neural Networks for Transfer Learning in Emotion Recognition","arxiv_id":"1706.03256","date":"2017-06-10","proceeding":null,"authors":["John Gideon","Soheil Khorram","Zakaria Aldeneh","Dimitrios Dimitriadis","Emily Mower Provost"],"abstract":"Many paralinguistic tasks are closely related and thus representations\nlearned in one domain can be leveraged for another. In this paper, we\ninvestigate how knowledge can be transferred between three paralinguistic\ntasks: speaker, emotion, and gender recognition. Further, we extend this\nproblem to cross-dataset tasks, asking how knowledge captured in one emotion\ndataset can be transferred to another. We focus on progressive neural networks\nand compare these networks to the conventional deep learning method of\npre-training and fine-tuning. Progressive neural networks provide a way to\ntransfer knowledge and avoid the forgetting effect present when pre-training\nneural networks on different tasks. Our experiments demonstrate that: (1)\nemotion recognition can benefit from using representations originally learned\nfor different paralinguistic tasks and (2) transfer learning can effectively\nleverage additional datasets to improve the performance of emotion recognition\nsystems.","url_abs":"http://arxiv.org/abs/1706.03256v1","url_pdf":"http://arxiv.org/pdf/1706.03256v1.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":"progressive-neural-networks-for-transfer","repo_url":"https://github.com/zbyte64/pytorch-dagsearch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.03256","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}