 |
ISBN
| 9783030367206 | |
DDC
| 006.31015 | |
Tác giả CN
| Calin, Ovidiu | |
Nhan đề
| Deep learning architectures : a mathematical approach / Ovidiu Calin | |
Thông tin xuất bản
| Cham : Springer, 2020 | |
Mô tả vật lý
| 768 p. : illustrations | |
Tùng thư
| Springer series in the data sciences. | |
Tóm tắt
| 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. | |
Từ khóa tự do
| Machine learning -- Mathematics. | |
Khoa
| Khoa Công nghệ Thông tin | |
Địa chỉ
| Thư Viện Đại học Nguyễn Tất Thành |
| |
000
| 00000nam#a2200000u##4500 |
|---|
| 001 | 25741 |
|---|
| 002 | 2 |
|---|
| 004 | 8E494138-2AF9-49A2-B464-C0FD75B7EC92 |
|---|
| 005 | 202204131410 |
|---|
| 008 | 201117s2020 ne eng |
|---|
| 009 | 1 0 |
|---|
| 020 | |a9783030367206 |
|---|
| 039 | |a20220413141048|bnghiepvu|c20201204151821|dtainguyendientu|y20201117151515|znghiepvu |
|---|
| 040 | |aNTT |
|---|
| 041 | |aeng |
|---|
| 044 | |ane |
|---|
| 082 | |a006.31015|bC154|223 |
|---|
| 100 | |aCalin, Ovidiu |
|---|
| 245 | |aDeep learning architectures : |ba mathematical approach / |cOvidiu Calin |
|---|
| 260 | |aCham : |bSpringer, |c2020 |
|---|
| 300 | |a768 p. : |billustrations |
|---|
| 490 | |aSpringer series in the data sciences. |
|---|
| 504 | |aIncludes bibliographical references (pages 749-758) and index. |
|---|
| 520 | |aThis 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. |
|---|
| 541 | |aKhoa CNTT tặng |
|---|
| 653 | |aMachine learning -- Mathematics. |
|---|
| 690 | |aKhoa Công nghệ Thông tin |
|---|
| 691 | |aCông nghệ thông tin |
|---|
| 852 | |aThư Viện Đại học Nguyễn Tất Thành |
|---|
| 856 | 1|uhttp://elib.ntt.edu.vn/documentdata01/2 tailieuthamkhao/000 tinhocthongtin/anhbiasach/25741_deeplearningamathematical_k_001thumbimage.jpg |
|---|
| 890 | |c1|a0|b0|d1 |
|---|
| |
Không tìm thấy biểu ghi nào
|
|
|
|