東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Neural networks with model compression

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Neural networks with model compression/ by Baochang Zhang ... [et al.].
其他作者:	Zhang, Baochang.
出版者:	Singapore :Springer Nature Singapore : : 2024.,
面頁冊數:	ix, 260 p. :ill., digital ;24 cm.
內容註:	Chapter 1. Introduction -- Chapter 2. Binary Neural Networks -- Chapter 3. Binary Neural Architecture Search -- Chapter 4. Quantization of Neural Networks -- Chapter 5. Network Pruning -- Chapter 6. Applications.
Contained By:	Springer Nature eBook
標題:	Neural networks (Computer science) -
電子資源:	https://doi.org/10.1007/978-981-99-5068-3
ISBN:	9789819950683

Neural networks with model compression
Neural networks with model compression[electronic resource] /by Baochang Zhang ... [et al.]. - Singapore :Springer Nature Singapore :2024. - ix, 260 p. :ill., digital ;24 cm. - Computational intelligence methods and applications,2510-1773. - Computational intelligence methods and applications..

Chapter 1. Introduction -- Chapter 2. Binary Neural Networks -- Chapter 3. Binary Neural Architecture Search -- Chapter 4. Quantization of Neural Networks -- Chapter 5. Network Pruning -- Chapter 6. Applications.

Deep learning has achieved impressive results in image classification, computer vision and natural language processing. To achieve better performance, deeper and wider networks have been designed, which increase the demand for computational resources. The number of floating-point operations (FLOPs) has increased dramatically with larger networks, and this has become an obstacle for convolutional neural networks (CNNs) being developed for mobile and embedded devices. In this context, our book will focus on CNN compression and acceleration, which are important for the research community. We will describe numerous methods, including parameter quantization, network pruning, low-rank decomposition and knowledge distillation. More recently, to reduce the burden of handcrafted architecture design, neural architecture search (NAS) has been used to automatically build neural networks by searching over a vast architecture space. Our book will also introduce NAS due to its superiority and state-of-the-art performance in various applications, such as image classification and object detection. We also describe extensive applications of compressed deep models on image classification, speech recognition, object detection and tracking. These topics can help researchers better understand the usefulness and the potential of network compression on practical applications. Moreover, interested readers should have basic knowledge about machine learning and deep learning to better understand the methods described in this book.

ISBN: 9789819950683

Standard No.: 10.1007/978-981-99-5068-3doiSubjects--Topical Terms:

532070
Neural networks (Computer science)

LC Class. No.: QA76.87

Dewey Class. No.: 006.32

Neural networks with model compression
LDR:02786nmm a2200337 a 4500 001 2368599
003 DE-He213
005 20240205005114.0
006 m d
007 cr nn 008maaau
008 241127s2024 si s 0 eng d
020 $a 9789819950683 $q (electronic bk.)
020 $a 9789819950676 $q (paper)
024 7 $a 10.1007/978-981-99-5068-3 $2 doi
035 $a 978-981-99-5068-3
040 $a GP $c GP
041 0 $a eng
050 4 $a QA76.87
072 7 $a UYQM $2 bicssc
072 7 $a COM004000 $2 bisacsh
072 7 $a UYQM $2 thema
082 0 4 $a 006.32 $2 23
090 $a QA76.87 $b .N494 2024
245 0 0 $a Neural networks with model compression $h [electronic resource] / $c by Baochang Zhang ... [et al.].
260 $a Singapore : $b Springer Nature Singapore : $b Imprint: Springer, $c 2024.
300 $a ix, 260 p. : $b ill., digital ; $c 24 cm.
490 1 $a Computational intelligence methods and applications, $x 2510-1773
505 0 $a Chapter 1. Introduction -- Chapter 2. Binary Neural Networks -- Chapter 3. Binary Neural Architecture Search -- Chapter 4. Quantization of Neural Networks -- Chapter 5. Network Pruning -- Chapter 6. Applications.
520 $a Deep learning has achieved impressive results in image classification, computer vision and natural language processing. To achieve better performance, deeper and wider networks have been designed, which increase the demand for computational resources. The number of floating-point operations (FLOPs) has increased dramatically with larger networks, and this has become an obstacle for convolutional neural networks (CNNs) being developed for mobile and embedded devices. In this context, our book will focus on CNN compression and acceleration, which are important for the research community. We will describe numerous methods, including parameter quantization, network pruning, low-rank decomposition and knowledge distillation. More recently, to reduce the burden of handcrafted architecture design, neural architecture search (NAS) has been used to automatically build neural networks by searching over a vast architecture space. Our book will also introduce NAS due to its superiority and state-of-the-art performance in various applications, such as image classification and object detection. We also describe extensive applications of compressed deep models on image classification, speech recognition, object detection and tracking. These topics can help researchers better understand the usefulness and the potential of network compression on practical applications. Moreover, interested readers should have basic knowledge about machine learning and deep learning to better understand the methods described in this book.
650 0 $a Neural networks (Computer science) $3 532070
650 1 4 $a Machine Learning. $3 3382522
650 2 4 $a Artificial Intelligence. $3 769149
650 2 4 $a Computer Imaging, Vision, Pattern Recognition and Graphics. $3 890871
650 2 4 $a Computer Vision. $3 3538524
700 1 $a Zhang, Baochang. $3 3712608
710 2 $a SpringerLink (Online service) $3 836513
773 0 $t Springer Nature eBook
830 0 $a Computational intelligence methods and applications. $3 3200598
856 4 0 $u https://doi.org/10.1007/978-981-99-5068-3
950 $a Computer Science (SpringerNature-11645)