Deep Learning and Practice with MindSpore

This book provides a comprehensive introduction to deep learning theory and its practical applications using the MindSpore AI computing framework. It is divided into 14 chapters and includes examples and links to online resources to help clarify complex topics.

Format: Hardback
Length: 394 pages
Publication date: 18 August 2021
Publisher: Springer Verlag, Singapore

This comprehensive book delves into the realm of deep learning, providing a systematic introduction to its theory and exploring its practical applications within the MindSpore AI computing framework. Spanning 14 chapters, the book comprehensively covers a wide range of topics, including deep learning, deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), unsupervised learning, deep reinforcement learning, automated machine learning, device-cloud collaboration, deep learning visualization, and data preparation for deep learning. To aid in understanding the intricate concepts explored, the book is accompanied by numerous examples and comprehensive links to online resources, making it an invaluable resource for both beginners and experts in the field.

Introduction:
Deep learning has emerged as a powerful tool in the field of artificial intelligence, enabling machines to learn and adapt from vast amounts of data. This book aims to provide a comprehensive guide to the theory and practical applications of deep learning, with a focus on the MindSpore AI computing framework.
Chapter 1: Deep Learning Fundamentals:
In this chapter, we will explore the basic concepts of deep learning, including neural networks, activation functions, and loss functions. We will also discuss the advantages and limitations of deep learning and its applications in various fields.
Chapter 2: Deep Neural Networks (DNNs):
DNNs are the building blocks of deep learning and are used for a wide range of tasks, such as image recognition, speech recognition, and natural language processing. We will examine the structure and functionality of DNNs, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs).
Chapter 3: Convolutional Neural Networks (CNNs):
CNNs are particularly effective at analyzing and extracting features from images. We will explore the architecture and training of CNNs, including convolutional layers, pooling layers, and fully connected layers. We will also discuss the use of CNNs in image classification, object detection, and facial recognition.
Chapter 4: Recurrent Neural Networks (RNNs):
RNNs are used for tasks that require sequential data processing, such as speech recognition and machine translation. We will examine the structure and training of RNNs, including gated recurrent units (GRUs) and long short-term memory (LSTM) cells. We will also discuss the use of RNNs in language modeling and text generation.
Chapter 5: Unsupervised Learning:
Unsupervised learning is a type of learning where the machine is given unlabeled data and has to find patterns and structures within it. We will explore the principles of unsupervised learning, including clustering, dimensionality reduction, and autoencoders. We will also discuss the use of unsupervised learning in image analysis, gene expression analysis, and social network analysis.
Chapter 6: Deep Reinforcement Learning:
Deep reinforcement learning is a type of learning where the machine learns to make decisions by interacting with an environment. We will explore the principles of deep reinforcement learning, including reward functions, policy gradients, and Monte Carlo methods. We will also discuss the use of deep reinforcement learning in autonomous driving, game playing, and robotics.
Chapter 7: Automated Machine Learning:
Automated machine learning is a method of building machine learning models without manual intervention. We will explore the principles of automated machine learning, including feature selection, model selection, and hyperparameter tuning. We will also discuss the use of automated machine learning in data mining, recommendation systems, and fraud detection.
Chapter 8: Device-Cloud Collaboration:
In the era of the Internet of Things (IoT), data processing and analysis require the collaboration between devices and the cloud. We will explore the principles of device-cloud collaboration, including data transmission, data storage, and data processing. We will also discuss the use of device-cloud collaboration in smart home automation, healthcare monitoring, and industrial control.
Chapter 9: Deep Learning Visualization:
Visualization is an important aspect of understanding and interpreting deep learning models. We will explore the principles of deep learning visualization, including tensor visualization, heatmap visualization, and 3D visualization. We will also discuss the use of deep learning visualization in medical imaging, finance, and sports analytics.
Chapter 10: Data Preparation for Deep Learning:
Data preparation is a critical step in the process of building and training deep learning models. We will explore the principles of data preparation, including data cleaning, data augmentation, and feature engineering. We will also discuss the use of data preparation in building and training deep learning models for image recognition, speech recognition, and natural language processing.
Conclusion:
Deep learning has revolutionized the field of artificial intelligence and has the potential to transform a wide range of industries. This book provides a comprehensive guide to the theory and practical applications of deep learning, with a focus on the MindSpore AI computing framework. By exploring the topics covered in this book, readers will gain a deep understanding of the principles and techniques of deep learning and will be able to apply them to their own projects.

Weight: 781g
Dimension: 235 x 155 (mm)
ISBN-13: 9789811622328
Edition number: 1st ed. 2021