When given a pattern and clear instruction on classification, a machine can learn quickly on a certain task. Cases are addressed to provide a sense of what\u2019s users\u2019 role in interactive machine learning: how does the machine influence the users and vice versa. Then, several features of people involving in interactive machine learning are stated as guidelines to understand the end-user effect on learning process: <\/p>\n\n\n\n
People are active, tend to give positive awards and they want\nto be a model for the learner. Also, with the nature of human intelligence,\nthey want to provide extra information in a rather simple decision, which lead\nto another feature that proper transparency in the system is valued by people\nand therefore help reduce error rate in labeling.<\/p>\n\n\n\n
Several guidelines are presented in the interactivity.\nInstead of a small number of professionals designing the system, people can involve\nmore in the process and collect the data they want. A novel interactive machine\nlearning system should be flexible on input and output: User could try input\nwith reasonable variation, assess the quality of the model and ask even the\nmodel directly; the output can be evaluated by the users rather than \u201cexperts\u201d,\na possible explanation of error case can be provided by users and the\nmodification of models is no longer forbidden for users.<\/p>\n\n\n\n
Details are discussed to further suggest what methods are\nbetter fit in a more interactive system: Common language, principles and\nguidelines, techniques and standards, volume handling, algorithm and\ncollaboration between HCI, etc. This paper laid a comprehensive foundation for\nfuture research on this topic.<\/p>\n\n\n\n
Reflection<\/strong><\/p>\n\n\n\n I once contributed to a dataset on sense making and explanation.\nMy job is to write two similar sentences where only one word (phrase) is different\n\u2013 one of them is common sense and the other is nonsense. For further\ninformation, I wrote three sentences trying to explain why the nonsense is\nappropriate, with only one of them best describe the reason. The model should\nunderstand the five sentences, pick the nonsense and find the best explanation.\nI was asked to be kind of extreme, for example, to write down a pair of \u201cI put\nan eggplant in the fridge\u201d and \u201cI put an elephant in the fridge\u201d. A mild\ndifference is not allowed, for example, \u201cI put a TV in the fridge.\u201d A model\nwill learn quickly for extreme comparison, however, I\u2019d prefer an iterative\nlearning process where the difference narrows down (Still one of them is\nnonsense and the other is common sense).<\/p>\n\n\n\n When I try to be a contributor on Figure Eight (previously CrowdFlower),\nthe tutorial and intro task is quite friendly. I was asked to identify a LinkedIn\naccount \u2013 whether he\/she \u2019s still working in the same position\/ same company. The\nassistance of decision makes me feel comfortable \u2013 I know what\u2019s my job and\nsome possible obstacles along the way, and I can tell the difficulties increase\nin a reasonable way. When there\u2019s more information in that cannot be described by\nselecting options, I\u2019m able to provide additional notes to the system, which\nmakes me feel that my work is valuable.<\/p>\n\n\n\n More interactivity is needed to improve the model into next\nlevel, but with a previous restricted rule and its restricted output, the\nopenness of the system is a crucial point to determine.<\/p>\n\n\n\n Question<\/strong><\/p>\n\n\n\n When given a pattern and clear instruction on classification, a machine can learn quickly on a certain task. Cases are addressed to provide a sense of what\u2019s users\u2019 role in interactive machine learning: how does the machine influence the users and vice versa. Then, several features of people involving in interactive machine learning are stated […]<\/p>\n","protected":false},"author":296,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[46,57],"class_list":["post-395","post","type-post","status-publish","format-standard","hentry","category-uncategorized","tag-class3","tag-powerpeople"],"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/wordpress.cs.vt.edu\/cs6724s20\/wp-json\/wp\/v2\/posts\/395","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wordpress.cs.vt.edu\/cs6724s20\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wordpress.cs.vt.edu\/cs6724s20\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wordpress.cs.vt.edu\/cs6724s20\/wp-json\/wp\/v2\/users\/296"}],"replies":[{"embeddable":true,"href":"https:\/\/wordpress.cs.vt.edu\/cs6724s20\/wp-json\/wp\/v2\/comments?post=395"}],"version-history":[{"count":1,"href":"https:\/\/wordpress.cs.vt.edu\/cs6724s20\/wp-json\/wp\/v2\/posts\/395\/revisions"}],"predecessor-version":[{"id":396,"href":"https:\/\/wordpress.cs.vt.edu\/cs6724s20\/wp-json\/wp\/v2\/posts\/395\/revisions\/396"}],"wp:attachment":[{"href":"https:\/\/wordpress.cs.vt.edu\/cs6724s20\/wp-json\/wp\/v2\/media?parent=395"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wordpress.cs.vt.edu\/cs6724s20\/wp-json\/wp\/v2\/categories?post=395"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wordpress.cs.vt.edu\/cs6724s20\/wp-json\/wp\/v2\/tags?post=395"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}