{"product_id":"deep-learning-principles-and-implementations-hardback-9781394256006","title":"Deep Learning; Principles and Implementations (Hardback) 9781394256006","description":"\u003cfont face=\"Georgia\"\u003e\r\n\u003cp\u003e\u003cfont size=\"6\"\u003eDeep Learning\u003c\/font\u003e\u003cbr\u003e\r\n\u003cfont size=\"5\"\u003ePrinciples and Implementations\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\r\n\r\n\u003cp\u003e\u003cfont size=\"4\"\u003eWeidong Kuang (Author)\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e9781394256006, Wiley\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003eHardback, published 1 April 2026\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e752 pages\u003cbr\u003e25.6 x 18.5 x 5.1 cm, 1.429 kg\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\r\n\r\n\r\n\u003cp align=\"justify\"\u003e\u003cstrong\u003e\u003cfont size=\"3\"\u003e\u003cp\u003e\u003cb\u003eA hands-on and intuitive guide to the foundations of modern deep learning\u003c\/b\u003e \u003c\/p\u003e\n\u003cp\u003eIn \u003ci\u003eDeep Learning: Principles and Implementations\u003c\/i\u003e, distinguished researcher and professor Weidong “Will” Kuang delivers an up-to-date exploration of how major deep learning algorithms and architectures are formalized and developed from mathematical equations. The book bridges theory and practice and covers a wide range of fundamental topics, including linear regression, logistic regression, basic neural networks, convolution neural networks, as well as other basic and advanced subjects in the field. \u003c\/p\u003e\n\u003cp\u003eThe author provides intuitive introductions to each subject and presents the development of algorithms and architectures from basic mathematical concepts. Along the way, he relies on straightforward math to keep the topics accessible for non-mathematicians and accompanies his explanations with tested Python sample code you can apply in your own work. \u003c\/p\u003e\n\u003cp\u003eYou’ll also find: \u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e Thorough introductions to both linear and logistic regression, offering a solid foundation and insight into neural networks\u003c\/li\u003e\n\u003cli\u003e Comprehensive explorations of neural networks, computer vision, natural language processing, generative models, and reinforcement learning\u003c\/li\u003e\n\u003cli\u003e Practical exercises that students and practitioners can use to apply and develop the concepts found in the book\u003c\/li\u003e\n\u003cli\u003e Balanced treatments of the mathematics, algorithms, architecture, and code that serve as the foundations of a complete understanding of deep learning\u003c\/li\u003e\n\u003c\/ul\u003e \u003cp\u003ePerfect for undergraduate and graduate students with an interest in deep learning, \u003ci\u003eDeep Learning: Principles and Implementations\u003c\/i\u003e will also benefit practicing software engineers, faculty, and researchers whose work involves deep learning and related topics.\u003c\/p\u003e\u003c\/font\u003e\u003c\/strong\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e\u003cp\u003ePreface xv\u003cbr\u003eMathematical Notation xxi\u003c\/p\u003e \u003cp\u003e\u003cb\u003e1 Introduction to Deep Learning 1\u003cbr\u003e\u003c\/b\u003e1.1 Introduction 1\u003cbr\u003e1.2 Types of Machine Learning 2\u003cbr\u003e1.3 Data Representation in Machine Learning 6\u003cbr\u003e1.4 An Overview of Deep Learning 8\u003cbr\u003e1.5 Resources for Deep Learning 14\u003c\/p\u003e \u003cp\u003e\u003cb\u003e2 Linear Regression 19\u003cbr\u003e\u003c\/b\u003e2.1 Linear Regression with Single Feature 19\u003cbr\u003e2.2 Linear Regression with Multiple Features 25\u003cbr\u003e2.3 Linear Models for Regression 28\u003cbr\u003e2.4 Linear Regression – a Probabilistic Perspective View 31\u003cbr\u003e2.5 An Example: House Price Prediction 35\u003cbr\u003e2.6 Summary and Further Reading 41\u003c\/p\u003e \u003cp\u003e\u003cb\u003e3 Classification and Logistic Regression 45\u003cbr\u003e\u003c\/b\u003e3.1 Logistic Regression 45\u003cbr\u003e3.2 Performance Metrics for Classification 52\u003cbr\u003e3.3 Implementation of Logistic Regression in Python 56\u003cbr\u003e3.4 Summary 61\u003c\/p\u003e \u003cp\u003e\u003cb\u003e4 Basics of Neural Networks 67\u003cbr\u003e\u003c\/b\u003e4.1 A Simplest Neural Network: A Logistic Regression Unit 67\u003cbr\u003e4.2 From Regression to Neural Networks 69\u003cbr\u003e4.3 Neural Network Representation: Feedforward Propagation 72\u003cbr\u003e4.4 Activation Functions 73\u003cbr\u003e4.5 Network Training: Backward Propagation 76\u003cbr\u003e4.6 Multi-class Classification: Softmax and Cross-Entropy Loss 79\u003cbr\u003e4.7 Practice in Python 82\u003cbr\u003e4.8 Summary and Further Reading 100\u003c\/p\u003e \u003cp\u003e\u003cb\u003e5 Practical Considerations in Neural Networks 107\u003cbr\u003e\u003c\/b\u003e5.1 Multiple-Layer Neural Networks 108\u003cbr\u003e5.2 Generalization and Model Selection 111\u003cbr\u003e5.3 Regularization 115\u003cbr\u003e5.4 Weight Initialization 119\u003cbr\u003e5.5 Mini-batch Gradient Descent 122\u003cbr\u003e5.6 Normalization 124\u003cbr\u003e5.7 Adam Optimization 129\u003cbr\u003e5.8 Gradient Checking 132\u003cbr\u003e5.9 Examples in Python 133\u003cbr\u003e5.10 Summary and Further Reading 166\u003c\/p\u003e \u003cp\u003e\u003cb\u003e6 Introduction to PyTorch 171\u003cbr\u003e\u003c\/b\u003e6.1 Why PyTorch? 171\u003cbr\u003e6.2 Tensors 172\u003cbr\u003e6.3 Data Representation Using Tensors 184\u003cbr\u003e6.4 Linear Regression Using PyTorch 189\u003cbr\u003e6.5 Neural Networks Using PyTorch 198\u003cbr\u003e6.6 Summary and Further Reading 203\u003c\/p\u003e \u003cp\u003e\u003cb\u003e7 Convolutional Neural Networks 205\u003cbr\u003e\u003c\/b\u003e7.1 Architecture of Convolutional Neural Networks 205\u003cbr\u003e7.2 Convolution Layer 207\u003cbr\u003e7.3 Pooling Layer and Fully Connected Layer 212\u003cbr\u003e7.4 Backpropagation in CNNs (Optional) 214\u003cbr\u003e7.5 Batch Normalization for CNNs 222\u003cbr\u003e7.6 Implement CNNs in PyTorch 223\u003cbr\u003e7.7 Summary and Further Reading 234\u003c\/p\u003e \u003cp\u003e\u003cb\u003e8 Classic Architectures of CNNs 239\u003cbr\u003e\u003c\/b\u003e8.1 Datasets 239\u003cbr\u003e8.2 AlexNet 243\u003cbr\u003e8.3 VGG: Networks Using Blocks 246\u003cbr\u003e8.4 GoogLeNet 249\u003cbr\u003e8.5 ResNet 250\u003cbr\u003e8.6 Pretrained Models 253\u003cbr\u003e8.7 Summary and Further Reading 265\u003c\/p\u003e \u003cp\u003e\u003cb\u003e9 Object Detection – YOLO 269\u003cbr\u003e\u003c\/b\u003e9.1 Introduction 269\u003cbr\u003e9.2 YOLO (v1) 270\u003cbr\u003e9.3 YOLO (v2) 276\u003cbr\u003e9.4 YOLO (v3) 280\u003cbr\u003e9.5 Implementation of YOLO v3 Using Pre-trained Model 289\u003cbr\u003e9.6 A Metric for Object Detection: mAP 310\u003cbr\u003e9.7 Summary and Further Reading 314\u003c\/p\u003e \u003cp\u003e\u003cb\u003e10 Introduction to Probabilistic Generative Models 319\u003cbr\u003e\u003c\/b\u003e10.1 Generative Models with Latent Variables 320\u003cbr\u003e10.2 EM Algorithm 323\u003cbr\u003e10.3 Variational Auto-encoder (VAE) 333\u003cbr\u003e10.4 VAE on MNIST Dataset in PyTorch 340\u003cbr\u003e10.5 Summary and Further Reading 348\u003c\/p\u003e \u003cp\u003e\u003cb\u003e11 Generative Adversarial Networks 351\u003cbr\u003e\u003c\/b\u003e11.1 Mathematical Description of the Original GAN 351\u003cbr\u003e11.2 Implementation of GANs 354\u003cbr\u003e11.3 Practical Issues with the Original GAN 362\u003cbr\u003e11.4 Conditional GAN 362\u003cbr\u003e11.5 InfoGAN 364\u003cbr\u003e11.6 Wasserstein GAN 367\u003cbr\u003e11.7 CycleGAN 372\u003cbr\u003e11.8 f-GANs 375\u003cbr\u003e11.9 Example: Deep Convolutional GAN on MNIST Dataset 378\u003cbr\u003e11.10 Summary and Further Reading 394\u003c\/p\u003e \u003cp\u003e\u003cb\u003e12 Diffusion Models 399\u003cbr\u003e\u003c\/b\u003e12.1 Revisit Variational Auto-Encoder 399\u003cbr\u003e12.3 Score-Based Generative Modeling 409\u003cbr\u003e12.4 Denoising Diffusion Implicit Models for Acceleration 417\u003cbr\u003e12.5 Guidance 421\u003cbr\u003e12.6 Implementation of a Simple Diffusion Model on MNIST Dataset 424\u003cbr\u003e12.7 Summary and Further Reading 436\u003c\/p\u003e \u003cp\u003e\u003cb\u003e13 Word Embedding 439\u003cbr\u003e\u003c\/b\u003e13.1 Introduction to Natural Language Processing 439\u003cbr\u003e13.2 Word2vec 442\u003cbr\u003e13.3 Hierarchical Softmax in Word2vec 452\u003cbr\u003e13.4 Negative Sampling in Word2vec 459\u003cbr\u003e13.5 GloVe 463\u003cbr\u003e13.6 Implementation of a Skip-Gram Model by PyTorch 464\u003cbr\u003e13.7 Summary and Further Reading 472\u003c\/p\u003e \u003cp\u003e\u003cb\u003e14 Recurrent Neural Networks 475\u003cbr\u003e\u003c\/b\u003e14.1 Introduction to Sequence Models 475\u003cbr\u003e14.2 Basic RNNs 476\u003cbr\u003e14.3 Long Short-Term Memory 482\u003cbr\u003e14.4 Practical RNN Architectures 486\u003cbr\u003e14.5 Sequence-to-Sequence Learning: An Application of RNNs 490\u003cbr\u003e14.6 Attention Mechanism in Encoder-Decoder Architectures 494\u003cbr\u003e14.7 BLEU: A Metric of Machine Translation 496\u003cbr\u003e14.8 Implementations of RNNs Using PyTorch 499\u003cbr\u003e14.9 Summary and Further Reading 504\u003c\/p\u003e \u003cp\u003e\u003cb\u003e15 Transformer 509\u003cbr\u003e\u003c\/b\u003e15.1 Bahdanau Attention Mechanism 510\u003cbr\u003e15.2 Attention Mechanism 512\u003cbr\u003e15.3 Transformer Architecture 514\u003cbr\u003e15.4 Bert 520\u003cbr\u003e15.5 Generative Pre-trained Transformer (GPT) 526\u003cbr\u003e15.6 Implementation of a Transformer in PyTorch 529\u003cbr\u003e15.7 Summary and Further Reading 543\u003c\/p\u003e \u003cp\u003e\u003cb\u003e16 Introduction to Reinforcement Learning 547\u003cbr\u003e\u003c\/b\u003e16.1 Definition of Markov Decision Process 547\u003cbr\u003e16.2 Policy, Value Function, and Bellman Equation 550\u003cbr\u003e16.3 Dynamic Programming for MDPs 557\u003cbr\u003e16.4 Monte Carlo Learning 560\u003cbr\u003e16.5 Temporal Difference Learning 564\u003cbr\u003e16.6 Implementation of Q-Learning for a Mountain Car Task 568\u003cbr\u003e16.7 Summary and Further Reading 575\u003c\/p\u003e \u003cp\u003e\u003cb\u003e17 Deep Q-Learning 579\u003cbr\u003e\u003c\/b\u003e17.1 Value Function Approximation 579\u003cbr\u003e17.2 Basic Deep Q-Network 582\u003cbr\u003e17.3 Double Deep Q-Network 585\u003cbr\u003e17.4 Implementation of DQN for Mountain Car-v 0 586\u003cbr\u003e17.5 Summary and Further Reading 595\u003c\/p\u003e \u003cp\u003e\u003cb\u003e18 Policy Gradient Methods 601\u003cbr\u003e\u003c\/b\u003e18.1 Introduction to Policy-Based Methods 601\u003cbr\u003e18.2 Policy Gradient Theorem 602\u003cbr\u003e18.3 REINFORCE Algorithm 605\u003cbr\u003e18.4 Actor-Critic Methods 609\u003cbr\u003e18.5 Policy Optimization Methods 613\u003cbr\u003e18.6 Deep Deterministic Policy Gradient (DDPG) 623\u003cbr\u003e18.7 Soft Actor-Critic Algorithm 627\u003cbr\u003e18.8 On-Policy and Off-Policy 631\u003cbr\u003e18.9 Implementations of Policy Gradient Algorithms in Python 633\u003cbr\u003e18.10 Summary and Further Reading 652\u003c\/p\u003e \u003cp\u003eExercises 653\u003cbr\u003eReferences 656\u003cbr\u003eAppendix A Mathematics in Machine Learning 657\u003cbr\u003eIndex 717\u003c\/p\u003e\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003eSubject Areas: Computer science [\u003ca title=\"See our other books on Computer science\" href=\"https:\/\/freshlyprintedbooks.co.uk\/search?q=%22Computer%20science%20%5BUY%5D%22\"\u003eUY\u003c\/a\u003e]\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\u003c\/font\u003e","brand":"Wiley","offers":[{"title":"Brand New","offer_id":52433237475608,"sku":"9781394256006","price":60.69,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0730\/2037\/5320\/files\/9781394256006.jpg?v=1784852633","url":"https:\/\/freshlyprintedbooks.co.uk\/products\/deep-learning-principles-and-implementations-hardback-9781394256006","provider":"Freshly Printed Books","version":"1.0","type":"link"}