Neural Networks with Model Compression
暫譯: 模型壓縮的神經網絡
Zhang, Baochang, Wang, Tiancheng, Xu, Sheng
- 出版商: Springer
- 出版日期: 2025-02-05
- 售價: $6,490
- 貴賓價: 9.5 折 $6,166
- 語言: 英文
- 頁數: 260
- 裝訂: Quality Paper - also called trade paper
- ISBN: 9819950708
- ISBN-13: 9789819950706
海外代購書籍(需單獨結帳)
相關主題
商品描述
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.
商品描述(中文翻譯)
深度學習在圖像分類、計算機視覺和自然語言處理方面取得了令人印象深刻的成果。為了達到更好的性能，設計了更深且更寬的網絡，這增加了對計算資源的需求。隨著網絡規模的擴大，浮點運算次數（FLOPs）急劇增加，這已成為卷積神經網絡（CNN）在移動和嵌入式設備上開發的一個障礙。在這個背景下，我們的書將專注於CNN的壓縮和加速，這對於研究社群來說非常重要。我們將描述多種方法，包括參數量化、網絡剪枝、低秩分解和知識蒸餾。最近，為了減少手工設計架構的負擔，神經架構搜索（NAS）被用來通過在廣泛的架構空間中搜索，自動構建神經網絡。我們的書也將介紹NAS，因為它在各種應用中具有優越性和最先進的性能，例如圖像分類和物體檢測。我們還描述了壓縮深度模型在圖像分類、語音識別、物體檢測和追蹤等方面的廣泛應用。這些主題可以幫助研究人員更好地理解網絡壓縮在實際應用中的實用性和潛力。此外，有興趣的讀者應具備基本的機器學習和深度學習知識，以便更好地理解本書中描述的方法。
作者簡介
Baochang Zhang is a full Professor with Institute of Artificial Intelligence, Beihang University, Beijing, China. He was selected by the Program for New Century Excellent Talents in University of Ministry of Education of China, also selected as Academic Advisor of Deep Learning Lab of Baidu Inc., and a distinguished researcher of Beihang Hangzhou Institute in Zhejiang Province. His research interests include explainable deep learning, computer vision and patter recognition. His HGPP and LDP methods were state-of-the-art feature descriptors, with 1234 and 768 Google Scholar citations, respectively. Both are "Test-of-Time" works. Our 1-bit methods achieved the best performance on ImageNet. His group also won the ECCV 2020 tiny object detection, COCO object detection, and ICPR 2020 Pollen recognition challenges.
Tiancheng Wang are pursuing their Ph.D. degrees under the supervision of Baochang Zhang. His research topics include model compression and trustworthy deep learning, and he has published several high-quality papers on deep model compression. He was selected as visiting student of Zhongguancun laboratory, Beijing, China.
Sheng Xu are pursuing their Ph.D. degrees under the supervision of Baochang Zhang. His research topics mainly focus on low-bit model compression, and he is one of the most active researchers in the field of binary neural networks. He has published more than 10 top-tier papers in computer vision with two of them are selected as CVPR oral papers.
Dr. David Doermann is a Professor of Empire Innovation at the University at Buffalo (UB) and the Director of the University at Buffalo Artificial Intelligence Institute. Prior to coming to UB, he was a program manager at the Defense Advanced Research Projects Agency (DARPA), where he developed, selected and oversaw approximately $150 million in research and transition funding in the areas ofcomputer vision, human language technologies and voice analytics. He coordinated performers on all of the projects, orchestrating consensus, evaluating cross team management and overseeing fluid program objectives.
作者簡介(中文翻譯)
張寶昌是中國北京航空航天大學人工智慧研究所的全職教授。他被中國教育部的新世紀優秀人才計畫選中，並被百度公司的深度學習實驗室選為學術顧問，還是浙江省北京航空航天大學杭州研究所的傑出研究員。他的研究興趣包括可解釋的深度學習、計算機視覺和模式識別。他的HGPP和LDP方法是最先進的特徵描述子，分別擁有1234和768次Google Scholar引用。這兩項都是「時代考驗」的作品。我們的1位元方法在ImageNet上達到了最佳性能。他的團隊還贏得了ECCV 2020微小物體檢測、COCO物體檢測和ICPR 2020花粉識別挑戰賽。
王天成在張寶昌的指導下攻讀博士學位。他的研究主題包括模型壓縮和可信的深度學習，並在深度模型壓縮方面發表了幾篇高質量的論文。他被選為中國北京的中關村實驗室的訪問學生。
徐晟在張寶昌的指導下攻讀博士學位。他的研究主題主要集中在低位元模型壓縮上，是二元神經網絡領域中最活躍的研究者之一。他在計算機視覺領域發表了超過10篇頂級論文，其中兩篇被選為CVPR口頭報告。
大衛·多曼博士是布法羅大學（UB）帝國創新教授及布法羅大學人工智慧研究所所長。在來到UB之前，他曾是國防高級研究計畫局（DARPA）的計畫經理，負責開發、選擇和監督約1.5億美元的研究和轉型資金，涵蓋計算機視覺、人類語言技術和語音分析等領域。他協調所有項目的執行者，促進共識，評估跨團隊管理並監督流暢的計畫目標。
