{"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/a-gray-box-interpretable-visual-debugging","title":"A Gray Box Interpretable Visual Debugging Approach for Deep Sequence Learning Model","arxiv_id":"1811.08374","date":"2018-11-20","proceeding":null,"authors":["Md Mofijul Islam","Amar Debnath","Tahsin Al Sayeed","Jyotirmay Nag Setu","Md Mahmudur Rahman","Md Sadman Sakib","Md Abdur Razzaque","Md. Mosaddek Khan","Swakkhar Shatabda"],"abstract":"Deep Learning algorithms are often used as black box type learning and they\nare too complex to understand. The widespread usability of Deep Learning\nalgorithms to solve various machine learning problems demands deep and\ntransparent understanding of the internal representation as well as decision\nmaking. Moreover, the learning models, trained on sequential data, such as\naudio and video data, have intricate internal reasoning process due to their\ncomplex distribution of features. Thus, a visual simulator might be helpful to\ntrace the internal decision making mechanisms in response to adversarial input\ndata, and it would help to debug and design appropriate deep learning models.\nHowever, interpreting the internal reasoning of deep learning model is not well\nstudied in the literature. In this work, we have developed a visual interactive\nweb application, namely d-DeVIS, which helps to visualize the internal\nreasoning of the learning model which is trained on the audio data. The\nproposed system allows to perceive the behavior as well as to debug the model\nby interactively generating adversarial audio data point. The web application\nof d-DeVIS is available at ddevis.herokuapp.com.","url_abs":"http://arxiv.org/abs/1811.08374v1","url_pdf":"http://arxiv.org/pdf/1811.08374v1.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":"a-gray-box-interpretable-visual-debugging","repo_url":"https://github.com/anon-conf/d-DeVIS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}