What do you think?
Rate this book
Deep Learning | 1st Edition | - Pearson
Deep Learning is designed as a textbook for undergraduate and postgraduate students, providing a strong foundation in deep learning concepts. The book begins with fundamental topics such as artificial intelligence, machine learning, natural language processing, image processing, and computer vision, which are essential for understanding deep learning technologies. Core deep learning concepts, including neural networks, activation functions, loss functions, optimization, and regularization, are explored in depth. Additionally, the book introduces data fundamentals, ensuring a complete learning experience.
The book covers major deep learning architectures, including Convolutional Neural Networks (CNNs) and Object Detection Networks, with discussions on R-CNN family algorithms, YOLO networks and image segmentation networks. Advanced CNN architectures such as AlexNet, VGGNet, InceptionNet, and ResNet are presented alongside transfer learning applications. The concepts of autoencoders and Recurrent Neural Networks (RNNs), including LSTMs and GRUs, are also introduced. Beyond CNNs, the book also explores Generative AI, covering Large Language Models (LLMs) such as ChatGPT and Generative Adversarial Networks (GANs). It introduces advanced topics like Transformer architectures, along with dedicated chapters on Restricted Boltzmann Machines (RBMs), Deep Belief Networks (DBNs), and Deep Reinforcement Learning algorithms.
Features –
📚 Deep learning concepts are presented in a clear, concise, and approachable manner, making complex topics easy to understand.
🔍 Hands-on Learning with an online Keras lab manual, enabling practical implementation of deep learning algorithms.
🌟 Extensive solved numerical problems, providing clarity and reinforcing deep learning concepts.
🎯 Comprehensive learning support, including summaries, glossaries, conceptual questions, numerical problems, and multiple-choice questions.
💡 Engaging pedagogical techniques, such as crossword puzzles and jumbled words, to reinforce key concepts.
The book covers major deep learning architectures, including Convolutional Neural Networks (CNNs) and Object Detection Networks, with discussions on R-CNN family algorithms, YOLO networks and image segmentation networks. Advanced CNN architectures such as AlexNet, VGGNet, InceptionNet, and ResNet are presented alongside transfer learning applications. The concepts of autoencoders and Recurrent Neural Networks (RNNs), including LSTMs and GRUs, are also introduced. Beyond CNNs, the book also explores Generative AI, covering Large Language Models (LLMs) such as ChatGPT and Generative Adversarial Networks (GANs). It introduces advanced topics like Transformer architectures, along with dedicated chapters on Restricted Boltzmann Machines (RBMs), Deep Belief Networks (DBNs), and Deep Reinforcement Learning algorithms.
Features –
📚 Deep learning concepts are presented in a clear, concise, and approachable manner, making complex topics easy to understand.
🔍 Hands-on Learning with an online Keras lab manual, enabling practical implementation of deep learning algorithms.
🌟 Extensive solved numerical problems, providing clarity and reinforcing deep learning concepts.
🎯 Comprehensive learning support, including summaries, glossaries, conceptual questions, numerical problems, and multiple-choice questions.
💡 Engaging pedagogical techniques, such as crossword puzzles and jumbled words, to reinforce key concepts.
1028 pages, Kindle Edition
Published March 26, 2025
1 person want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
No one has reviewed this book yet.