发帖
雷达卡
M.S. Ramaiah Institute of Technology, Bengaluru (VTU)
Textbook:Cloud-based Multi-Modal Information Analytics: A Hands-on Approach
Author(s): Srinidhi Hiriyannaiah
Course descrition:
This course provides different dimensions of multi-modal and deep learning methods using three different modalities, including video, audio and image information. The solutions presented leverage both spatial and temporal information from multi-modal data and effectively integrate them for interpretation and analysis. The book is divided into three parts and ten chapters. Part I discusses the introduction to multi-modal data and analytics that describes various modalities of data. Subsequently, Part II highlights the different architectures used in analytics of multi-modal data. After that, Part III provides various application-centric examples of different modalities, including video, audio and image. This book also provides a platform for most recent research on using deep learning-based solutions for multi-modal data analytics. The book is logically divided into three parts. The first part deals with the gentle introduction to cloud-based multi-model data analytics, the second part provides an architecture and suitable examples for multi-modal data and analytics using cloud, and, finally, the third part explores different cloud-based applications that require multi-modal analytics.
Chapter 1 provides an overview of multi-modal data analytics and life-
cycle of development of an application using cloud-based utilities. It introduces the various types of multi-modal data and their applications and challenges of multi-modal data analytics.
Chapter 2 explores the different Google Cloud services, storage and computer engine. It also briefs how to work with Google Colaboratory.
Chapter 3 provides an overview of deep learning.
Chapter 4 focuses on deep learning platforms like OpenCV, PyTorch,
TensorFlow and Keras.
Chapter 5 discusses the use of neural network models like CNN, RNN,
LSTM and GRU for multi-modal data analytics.
Chapter 6 provides illustrative examples of neural networks multi-modal
architectures like AlexNet, VGG-16 and YoloV3.
Chapter 7 presents a step-by-step procedure to be adopted for training
neural networks on cloud, including use of distributed training, setting up of hyperparameters and optimization.
Chapter 8 provides a classical example of image analytics using Google Cloud.
Chapter 9 explores yet another classical example of text analytics via Google Cloud.
Chapter 10 concludes the book by exploring the deployment of speech analytics on Google Cloud.
Cloud-based Multi-Modal Information Analytics_ A Hands-on Approach .pdf
(36.73 MB, 需要: RMB 29 元)
京公网安备 11010802022788号
