國立高雄大學圖資館 |

登入

回首頁

Towards explainable fuzzy AIconcepts, paradigms, tools, and techniques /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Towards explainable fuzzy AIby Vladik Kreinovich.
其他題名:	concepts, paradigms, tools, and techniques /
作者:	Kreinovich, Vladik.
出版者:	Cham :Springer International Publishing :2022.
面頁冊數:	x, 130 p. :ill., digital ;24 cm.
Contained By:	Springer Nature eBook
標題:	Artificial intelligence.
電子資源:	https://doi.org/10.1007/978-3-031-09974-8
ISBN:	9783031099748$q(electronic bk.)

Towards explainable fuzzy AIconcepts, paradigms, tools, and techniques /
Kreinovich, Vladik.

Towards explainable fuzzy AIconcepts, paradigms, tools, and techniques /[electronic resource] :by Vladik Kreinovich. - Cham :Springer International Publishing :2022. - x, 130 p. :ill., digital ;24 cm. - Studies in computational intelligence,v. 10471860-9503 ;. - Studies in computational intelligence ;v. 216..

Why Explainable AI? Why Fuzzy Explainable AI? What Is Fuzzy? -- Defuzzification -- Which Fuzzy Techniques? -- So How Can We Design Explainable Fuzzy AI: Ideas -- How to Make Machine Learning Itself More Explainable -- Final Self-Test.

Modern AI techniques -- especially deep learning -- provide, in many cases, very good recommendations: where a self-driving car should go, whether to give a company a loan, etc. The problem is that not all these recommendations are good -- and since deep learning provides no explanations, we cannot tell which recommendations are good. It is therefore desirable to provide natural-language explanation of the numerical AI recommendations. The need to connect natural language rules and numerical decisions is known since 1960s, when the need emerged to incorporate expert knowledge -- described by imprecise words like "small" -- into control and decision making. For this incorporation, a special "fuzzy" technique was invented, that led to many successful applications. This book described how this technique can help to make AI more explainable.The book can be recommended for students, researchers, and practitioners interested in explainable AI.

ISBN: 9783031099748$q(electronic bk.)

Standard No.: 10.1007/978-3-031-09974-8doiSubjects--Topical Terms:

194058
Artificial intelligence.

LC Class. No.: Q335 / .K74 2022

Dewey Class. No.: 006.3

Towards explainable fuzzy AIconcepts, paradigms, tools, and techniques /
LDR:02269nmm a2200337 a 4500 001 630591
003 DE-He213
005 20220916063426.0
006 m d
007 cr nn 008maaau
008 230329s2022 sz s 0 eng d
020 $a 9783031099748$q(electronic bk.)
020 $a 9783031099731$q(paper)
024 7 $a 10.1007/978-3-031-09974-8 $2 doi
035 $a 978-3-031-09974-8
040 $a GP $c GP
041 0 $a eng
050 4 $a Q335 $b .K74 2022
072 7 $a UYQ $2 bicssc
072 7 $a TEC009000 $2 bisacsh
072 7 $a UYQ $2 thema
082 0 4 $a 006.3 $2 23
090 $a Q335 $b .K92 2022
100 1 $a Kreinovich, Vladik. $3 610822
245 1 0 $a Towards explainable fuzzy AI $h [electronic resource] : $b concepts, paradigms, tools, and techniques / $c by Vladik Kreinovich.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2022.
300 $a x, 130 p. : $b ill., digital ; $c 24 cm.
490 1 $a Studies in computational intelligence, $x 1860-9503 ; $v v. 1047
505 0 $a Why Explainable AI? Why Fuzzy Explainable AI? What Is Fuzzy? -- Defuzzification -- Which Fuzzy Techniques? -- So How Can We Design Explainable Fuzzy AI: Ideas -- How to Make Machine Learning Itself More Explainable -- Final Self-Test.
520 $a Modern AI techniques -- especially deep learning -- provide, in many cases, very good recommendations: where a self-driving car should go, whether to give a company a loan, etc. The problem is that not all these recommendations are good -- and since deep learning provides no explanations, we cannot tell which recommendations are good. It is therefore desirable to provide natural-language explanation of the numerical AI recommendations. The need to connect natural language rules and numerical decisions is known since 1960s, when the need emerged to incorporate expert knowledge -- described by imprecise words like "small" -- into control and decision making. For this incorporation, a special "fuzzy" technique was invented, that led to many successful applications. This book described how this technique can help to make AI more explainable.The book can be recommended for students, researchers, and practitioners interested in explainable AI.
650 0 $a Artificial intelligence. $3 194058
650 0 $a Fuzzy logic. $3 181981
650 1 4 $a Computational Intelligence. $3 338479
650 2 4 $a Artificial Intelligence. $3 212515
650 2 4 $a Data Engineering. $3 839346
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
830 0 $a Studies in computational intelligence ; $v v. 216. $3 380871
856 4 0 $u https://doi.org/10.1007/978-3-031-09974-8
950 $a Intelligent Technologies and Robotics (SpringerNature-42732)