An Introduction to Deep Visual Explanation

An Introduction to Deep Visual Explanation. Babiker, H. K. B. & Goebel, R. arXiv:1711.09482 [cs, stat], March, 2018. arXiv: 1711.09482

Paper abstract bibtex

The practical impact of deep learning on complex supervised learning problems has been signiﬁcant, so much so that almost every Artiﬁcial Intelligence problem, or at least a portion thereof, has been somehow recast as a deep learning problem. The applications appeal is signiﬁcant, but this appeal is increasingly challenged by what some call the challenge of explainability, or more generally the more traditional challenge of debuggability: if the outcomes of a deep learning process produce unexpected results (e.g., less than expected performance of a classiﬁer), then there is little available in the way of theories or tools to help investigate the potential causes of such unexpected behavior, especially when this behavior could impact people’s lives.

@article{babiker_introduction_2018,
	title = {An {Introduction} to {Deep} {Visual} {Explanation}},
	url = {http://arxiv.org/abs/1711.09482},
	abstract = {The practical impact of deep learning on complex supervised learning problems has been signiﬁcant, so much so that almost every Artiﬁcial Intelligence problem, or at least a portion thereof, has been somehow recast as a deep learning problem. The applications appeal is signiﬁcant, but this appeal is increasingly challenged by what some call the challenge of explainability, or more generally the more traditional challenge of debuggability: if the outcomes of a deep learning process produce unexpected results (e.g., less than expected performance of a classiﬁer), then there is little available in the way of theories or tools to help investigate the potential causes of such unexpected behavior, especially when this behavior could impact people’s lives.},
	language = {en},
	urldate = {2022-01-19},
	journal = {arXiv:1711.09482 [cs, stat]},
	author = {Babiker, Housam Khalifa Bashier and Goebel, Randy},
	month = mar,
	year = {2018},
	note = {arXiv: 1711.09482},
	keywords = {/unread, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Statistics - Machine Learning, ⛔ No DOI found},
}

Downloads: 0

{"_id":"7EmdX6qENq5kGYwJn","bibbaseid":"babiker-goebel-anintroductiontodeepvisualexplanation-2018","author_short":["Babiker, H. K. B.","Goebel, R."],"bibdata":{"bibtype":"article","type":"article","title":"An Introduction to Deep Visual Explanation","url":"http://arxiv.org/abs/1711.09482","abstract":"The practical impact of deep learning on complex supervised learning problems has been signiﬁcant, so much so that almost every Artiﬁcial Intelligence problem, or at least a portion thereof, has been somehow recast as a deep learning problem. The applications appeal is signiﬁcant, but this appeal is increasingly challenged by what some call the challenge of explainability, or more generally the more traditional challenge of debuggability: if the outcomes of a deep learning process produce unexpected results (e.g., less than expected performance of a classiﬁer), then there is little available in the way of theories or tools to help investigate the potential causes of such unexpected behavior, especially when this behavior could impact people’s lives.","language":"en","urldate":"2022-01-19","journal":"arXiv:1711.09482 [cs, stat]","author":[{"propositions":[],"lastnames":["Babiker"],"firstnames":["Housam","Khalifa","Bashier"],"suffixes":[]},{"propositions":[],"lastnames":["Goebel"],"firstnames":["Randy"],"suffixes":[]}],"month":"March","year":"2018","note":"arXiv: 1711.09482","keywords":"/unread, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Statistics - Machine Learning, ⛔ No DOI found","bibtex":"@article{babiker_introduction_2018,\n\ttitle = {An {Introduction} to {Deep} {Visual} {Explanation}},\n\turl = {http://arxiv.org/abs/1711.09482},\n\tabstract = {The practical impact of deep learning on complex supervised learning problems has been signiﬁcant, so much so that almost every Artiﬁcial Intelligence problem, or at least a portion thereof, has been somehow recast as a deep learning problem. The applications appeal is signiﬁcant, but this appeal is increasingly challenged by what some call the challenge of explainability, or more generally the more traditional challenge of debuggability: if the outcomes of a deep learning process produce unexpected results (e.g., less than expected performance of a classiﬁer), then there is little available in the way of theories or tools to help investigate the potential causes of such unexpected behavior, especially when this behavior could impact people’s lives.},\n\tlanguage = {en},\n\turldate = {2022-01-19},\n\tjournal = {arXiv:1711.09482 [cs, stat]},\n\tauthor = {Babiker, Housam Khalifa Bashier and Goebel, Randy},\n\tmonth = mar,\n\tyear = {2018},\n\tnote = {arXiv: 1711.09482},\n\tkeywords = {/unread, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Statistics - Machine Learning, ⛔ No DOI found},\n}\n\n","author_short":["Babiker, H. K. B.","Goebel, R."],"key":"babiker_introduction_2018","id":"babiker_introduction_2018","bibbaseid":"babiker-goebel-anintroductiontodeepvisualexplanation-2018","role":"author","urls":{"Paper":"http://arxiv.org/abs/1711.09482"},"keyword":["/unread","Computer Science - Computer Vision and Pattern Recognition","Computer Science - Machine Learning","Statistics - Machine Learning","⛔ No DOI found"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/victorjhu","dataSources":["CmHEoydhafhbkXXt5"],"keywords":["/unread","computer science - computer vision and pattern recognition","computer science - machine learning","statistics - machine learning","⛔ no doi found"],"search_terms":["introduction","deep","visual","explanation","babiker","goebel"],"title":"An Introduction to Deep Visual Explanation","year":2018}