國立虎尾科技大學 |

登入

回首頁

Interpretable AI : = building explainable machine learning systems /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Interpretable AI :/ Ajay Thampi.
其他題名:	building explainable machine learning systems /
作者:	Thampi, Ajay,
出版者:	Shelter Island, NY :Manning Publications, : c2022.,
面頁冊數:	xxi, 304 p. :ill. ; : 24 cm.;
附註:	Includes index.
標題:	Artificial intelligence. -
ISBN:	9781617297649 (pbk.) :

Interpretable AI : = building explainable machine learning systems /
Thampi, Ajay,

Interpretable AI :building explainable machine learning systems /Ajay Thampi. - Shelter Island, NY :Manning Publications,c2022. - xxi, 304 p. :ill. ;24 cm.

Includes index.

It's often difficult to explain how deep learning models work, even for the data scientists who create them. Improving transparency and interpretability in machine learning models minimizes errors, reduces unintended bias, and increases trust in the outcomes. This unique book contains techniques for looking inside "black box" models, designing accountable algorithms, and understanding the factors that cause skewed results. "Interpretable AI" teaches you to identify the patterns your model has learned and why it produces its results. As you read, you'll pick up algorithm-specific approaches, like interpreting regression and generalized additive models, along with tips to improve performance during training. You'll also explore methods for interpreting complex deep learning models where some processes are not easily observable. AI transparency is a fast-moving field, and this book simplifies cutting-edge research into practical methods you can implement with Python.--

ISBN: 9781617297649 (pbk.) :NT1924

LCCN: 2022289405Subjects--Topical Terms:

559380
Artificial intelligence.

LC Class. No.: Q335 / .T468 2022

Dewey Class. No.: 006.3

Interpretable AI : = building explainable machine learning systems /
LDR:01704cam a2200229 a 4500 001 1079350
005 20221110225423.0
008 221117s2022 nyua 001 0 eng d
010 $a 2022289405
020 $a 9781617297649 (pbk.) : $c NT1924
020 $a 161729764X (pbk.)
035 $a (OCoLC)1289289834
035 $a on1289289834
040 $a UKMGB $b eng $c NFU $d UKMGB $d OCLCF $d BDX $d JRZ
041 0 # $a eng
042 $a lccopycat
050 0 0 $a Q335 $b .T468 2022
082 0 4 $a 006.3 $2 23
100 1 $a Thampi, Ajay, $e author. $3 1383508
245 1 0 $a Interpretable AI : $b building explainable machine learning systems / $c Ajay Thampi.
260 # $a Shelter Island, NY : $b Manning Publications, $c c2022.
300 $a xxi, 304 p. : $b ill. ; $c 24 cm.
500 $a Includes index.
520 # $a It's often difficult to explain how deep learning models work, even for the data scientists who create them. Improving transparency and interpretability in machine learning models minimizes errors, reduces unintended bias, and increases trust in the outcomes. This unique book contains techniques for looking inside "black box" models, designing accountable algorithms, and understanding the factors that cause skewed results. "Interpretable AI" teaches you to identify the patterns your model has learned and why it produces its results. As you read, you'll pick up algorithm-specific approaches, like interpreting regression and generalized additive models, along with tips to improve performance during training. You'll also explore methods for interpreting complex deep learning models where some processes are not easily observable. AI transparency is a fast-moving field, and this book simplifies cutting-edge research into practical methods you can implement with Python.-- $c Source other than the Library of Congress.
650 # 0 $a Artificial intelligence. $3 559380
650 # 0 $a Machine learning. $3 561253
650 # 0 $a Python (Computer program language) $3 566246
650 # 2 $a Artificial Intelligence. $3 646849