建國科技大學圖書館 |

語系: 繁體中文

說明(常見問題)

圖書館個人資料蒐集告知聲明

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Deep learning architectures : a math...

Calin, Ovidiu.

Deep learning architectures : a mathematical approach

紀錄類型:	書目-語言資料,印刷品 : 單行本
副題名:	a mathematical approach
作者:	CalinOvidiu.,
出版地:	Cham
出版者:	Springer;
出版年:	2020.
面頁冊數:	xxx, 760 p.ill. : 26 cm.;
集叢名:	Springer Series in the Data Sciences Ser.
標題:	Machine learning - Mathematics. -
摘要註:	This book describes how neural networks operate from the mathematical point of view. As a result, neural networks can be interpreted both as function universal approximators and information processors. The book bridges the gap between ideas and concepts of neural networks, which are used nowadays at an intuitive level, and the precise modern mathematical language, presenting the best practices of the former and enjoying the robustness and elegance of the latter. This book can be used in a graduate course in deep learning, with the first few parts being accessible to senior undergraduates. In addition, the book will be of wide interest to machine learning researchers who are interested in a theoretical understanding of the subject.
ISBN:	9783030367237

Deep learning architectures : a mathematical approach
Calin, Ovidiu.

Deep learning architectures : a mathematical approach / Ovidiu Calin. - Cham : Springer, 2020.. - xxx, 760 p. ; ill. ; 26 cm.. - (Springer Series in the Data Sciences Ser.).
Includes bibliographical references (p. 741-750) and index..
ISBN 9783030367237ISBN 3030367231
Machine learning -- Mathematics.

Deep learning architectures : a mathematical approach
LDR:01583cam a2200265 450 001 396466
009 022422871
010 1 $a 9783030367237 $b pbk. $d NT1960
010 1 $a 3030367231 $b pbk.
010 1 $z 3030367215 $b ebk.
010 1 $z 9783030367213 $b ebk.
100 $a 20211120d2020 k y0engy50 b
101 0 $a eng
102 $a ch
105 $a a a 001yy
200 1 $a Deep learning architectures $e a mathematical approach $f Ovidiu Calin.
210 $a Cham $c Springer $d 2020.
215 1 $a xxx, 760 p. $c ill. $d 26 cm.
225 2 $a Springer Series in the Data Sciences Ser.
320 $a Includes bibliographical references (p. 741-750) and index.
330 $a This book describes how neural networks operate from the mathematical point of view. As a result, neural networks can be interpreted both as function universal approximators and information processors. The book bridges the gap between ideas and concepts of neural networks, which are used nowadays at an intuitive level, and the precise modern mathematical language, presenting the best practices of the former and enjoying the robustness and elegance of the latter. This book can be used in a graduate course in deep learning, with the first few parts being accessible to senior undergraduates. In addition, the book will be of wide interest to machine learning researchers who are interested in a theoretical understanding of the subject.
410 0 $1 2001 $a Springer series in the data sciences.
410 0 $1 2001 $a Springer Series in the Data Sciences Ser.
606 $a Machine learning $x Mathematics. $2 lc $3 385670
676 $a 006.3/101/51 $v 23
680 $a Q325.5
700 1 $a Calin $b Ovidiu. $3 389130
801 0 $a cw $b CTU $c 20211120 $g AACR2