Deep learning: a visual approach
"A practical, thorough introduction to deep learning, without the usage of advanced math or programming. Covers topics such as image classification, text generation, and the machine learning techniques that are the basis of modern AI"--
Saved in:
| Main Author: | |
|---|---|
| Format: | Book |
| Language: | English |
| Published: |
San Francisco, CA
No Starch Press, Inc.
[2021]
|
| Subjects: | |
| Online Access: | Inhaltsverzeichnis |
| Summary: | "A practical, thorough introduction to deep learning, without the usage of advanced math or programming. Covers topics such as image classification, text generation, and the machine learning techniques that are the basis of modern AI"-- |
| Physical Description: | xxviii, 736 Seiten Illustrationen, Diagramme 24 cm |
| ISBN: | 9781718500723 |
Staff View
MARC
| LEADER | 00000nam a22000008c 4500 | ||
|---|---|---|---|
| 001 | BV047403729 | ||
| 003 | DE-604 | ||
| 005 | 20250116 | ||
| 007 | t| | ||
| 008 | 210805s2021 xx a||| b||| 00||| eng d | ||
| 020 | |a 9781718500723 |9 978-1-7185-0072-3 | ||
| 035 | |a (OCoLC)1263166253 | ||
| 035 | |a (DE-599)BVBBV047403729 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-739 |a DE-573 |a DE-83 |a DE-522 |a DE-Aug4 |a DE-92 |a DE-1043 |a DE-858 | ||
| 084 | |a ST 302 |0 (DE-625)143652: |2 rvk | ||
| 084 | |a ST 301 |0 (DE-625)143651: |2 rvk | ||
| 084 | |a ST 300 |0 (DE-625)143650: |2 rvk | ||
| 084 | |a 68T05 |2 msc | ||
| 100 | 1 | |a Glassner, Andrew S. |d 1960- |0 (DE-588)13836043X |4 aut | |
| 245 | 1 | 0 | |a Deep learning |b a visual approach |c Andrew Glassner |
| 264 | 1 | |a San Francisco, CA |b No Starch Press, Inc. |c [2021] | |
| 300 | |a xxviii, 736 Seiten |b Illustrationen, Diagramme |c 24 cm | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 505 | 8 | |a Part I: Foundational ideas -- An overview of machine learning -- Essential statistics -- Measuring performance -- Bayes' rule -- Curves and surfaces -- Information theory -- Part II: Basic machine learning -- Classification -- Training and testing -- Overfitting and underfitting -- Data preparation -- Classifiers -- Ensembles -- Part III: Deep learning basics -- Neural networks -- Backpropagation -- Optimizers -- Part IV: Beyond the basics -- Convolutional neural networks -- Convnets in practice -- Autoencoders -- Recurrent neural networks -- Attention and transformers -- Reinforcement learning -- Generative adversarial networks -- Creative applications | |
| 520 | 3 | |a "A practical, thorough introduction to deep learning, without the usage of advanced math or programming. Covers topics such as image classification, text generation, and the machine learning techniques that are the basis of modern AI"-- | |
| 650 | 0 | 7 | |a Deep Learning |0 (DE-588)1135597375 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |2 gnd |9 rswk-swf |
| 653 | 0 | |a Machine learning | |
| 653 | 0 | |a Neural networks (Computer science) | |
| 653 | 0 | |a Artificial intelligence | |
| 653 | 0 | |a Neural networks (Computer science) | |
| 653 | 0 | |a Machine learning | |
| 653 | 6 | |a Handbooks and manuals | |
| 689 | 0 | 0 | |a Deep Learning |0 (DE-588)1135597375 |D s |
| 689 | 0 | 1 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |D s |
| 689 | 0 | |5 DE-604 | |
| 776 | 0 | 8 | |i Online version |a Glassner, Andrew |t Deep learning |d San Francisco, CA : No Starch Press, Inc., [2021] |z 9781718500730 |
| 856 | 4 | 2 | |m Digitalisierung UB Passau - ADAM Catalogue Enrichment |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=032804748&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 943 | 1 | |a oai:aleph.bib-bvb.de:BVB01-032804748 | |
Record in the Search Index
| _version_ | 1823932148345733120 |
|---|---|
| adam_text |
BRIEF CONTENTS Acknowledgments. xxi Introduction. xxiii PART I: FOUNDATIONAL IDEAS.1 Chapter 1 : An Overview of Machine Learning.3 Chapter 2: Essential Statistics. 15 Chapter 3: Measuring Performance. 47 Chapter 4: Bayes' Rule.83 Chapter 5: Curves and Surfaces. 117 Chapter 6: Information Theory.133 PART II: BASIC MACHINE LEARNING. 153 Chapter 7: Classification.155 Chapter 8: Training and Testing. 181 Chapter 9: Overfitting and
Underfitting. 195 Chapter 10: Data Preparation. 221 Chapter 11 : Classifiers. 263 Chapter 12: Ensembles. 297 PART III: DEEP LEARNING BASICS. 311 Chapter 13: Neural Networks. 313 Chapter 14: Backpropagation. 351 Chapter 15: Optimizers 387
PART IV: BEYOND THE BASICS.427 Chapter 16: Convolutional Neural Networks.429 Chapter 17: Convnets in Practice. 473 Chapter 18: Autoencoders.495 Chapter 19: Recurrent Neural Networks.539 Chapter 20: Attention and Transformers.565 Chapter 21 : Reinforcement Learning. 601 Chapter 22: Generative Adversarial Networks. 649 Chapter 23: Creative Applications. 675 References. 693 Image Credits.717 Index.721 X Brief Contents
CONTENTS IN DETAIL ACKNOWLEDGMENTS INTRODUCTION xxi xxiii Who This Book Is For.xxiv This Book Has No Math and No Code.xxv There Is Code, If You Want It. xxv The Figures Are Available, Too!. xxv Errata.xxvi About This Book. xxvi Part I: Foundational Ideas.xxvi Part II: Basic Machine Learning. xxvii Part III: Deep Learning Basics. xxvii Part IV: Deep Beyond the Basics.xxvii Final Words. xxviii PART I: FOUNDATIONAL IDEAS 1 1 AN OVERVIEW OF MACHINELEARNING 3 Expert
Systems.4 Supervised Learning. 6 Unsupervised Learning.8 Reinforcement Learning . 9 Deep Learning. 10 Summary. 13 2 ESSENTIAL STATISTICS 15 Describing Randomness. 16 Random Variables and Probability Distributions . 17 Some Common Distributions.21 Continuous Distributions.21 Discrete Distributions. 26 Collections of Random Values.28 Expected
Value. 28 Dependence.29 Independent and Identically Distributed Variables.29 Sampling and Replacement. 29 Selection with Replacement.30 Selection Without Replacement. 30 Bootstrapping. 31 Covariance and Correlation. 35 Covariance.36 Correlation. 37
Statistics Don't Tell Us Everything.40 High-Dimensional Spaces. 42 Summary. 44 3 MEASURING PERFORMANCE 47 Different Types of Probability.48 Dart Throwing.48 Simple Probability. 50 Conditional Probability.50 Joint Probability.53 Marginal Probability.55 Measuring Correctness. 56 Classifying Samples.57 The Confusion Matrix. 60 Characterizing Incorrect
Predictions.61 Measuring Correct and Incorrect. 63 Accuracy. 64 Precision. 65 Recall. 66 Precision-Recall Tradeoff.67 Misleading Measures. 69 fl Score.71 About These Terms. 72 Other Measures.72 Constructing a Confusion Matrix Correctly.74 Summary.81 4 BAYES' RULE 83 Frequentisi and Bayesian Probability. 84 The
Frequentisi Approach.84 The Bayesian Approach. 85 Frequentists vs. Bayesians. 85 Frequentisi Coin Flipping. 86 Bayesian Coin Flipping. 87 A Motivating Example. 87 Picturing the Coin Probabilities. 88 Expressing Coin Flips as Probabilities.90 Bayes' Rule.94 Discussion of Bayes' Rule.95 Bayes' Rule and Confusion Matrices. 97 Repeating Bayes'Rule. 101 The Posterior-Prior Loop. 102 The Bayes Loop in
Action. 103 Multiple Hypotheses. 109 Summary. 115 XH Contents in Detail
5 CURVES AND SURFACES 117 The Nature of Functions. The Derivative. Maximums and Minimums. Tangent Lines. Finding Minimums and Maximums with Derivatives. The Gradient. Water, Gravity, and the Gradient. Finding Maximums and Minimums with Gradients. Saddle Points. Summary. 118 119 119 122 125 126 127 128 130 131 6 INFORMATION THEORY 133 Surprise and Context. Understanding Surprise. Unpacking Context.
Measuring Information. Adaptive Codes. Speaking Morse. Customizing Morse Code. Entropy. Cross Entropy. Two Adaptive Codes. Using the Codes. Cross Entropy in Practice. Kullback-Leibler Divergence. Summary. PART II: BASIC MACHINE LEARNING 134 134 135 136 137 138 141 143 145 146 148 150 151 152 153 7 CLASSIFICATION 155 Two-Dimensional Binary Classification. 2D Multiclass
Classification. Multiclass Classification. One-Versus-Rest. One-Versus-One. Clustering. The Curse of Dimensionality. Dimensionality and Density. High-Dimensional Weirdness. Summary. 156 160 161 161 163 166 168 169 175 179 Contents in Detail
8 TRAINING AND TESTING 181 Training. Testing the Performance. Test Data. Validation Data. Cross-Validation. k-Fold Cross-Validation. Summary. 9 OVERFITTING AND UNDERFITTING 182 183 1 86 187 190 192 194 195 Finding a Good Fit. 196 Overfitting. 196 Underfitting. 197 Detecting and Addressing Overfitting. 197 Early
Stopping.202 Regularization.203 Bias and Variance. 204 Matching the Underlying Data.205 High Bias, Low Variance. 207 Low Bias, High Variance. 209 Comparing Curves.210 Fitting a Line with Bayes' Rule. 212 Summary. 219 10 DATA PREPARATION 221 Basic Data Cleaning.222 The Importance of Consistency. 223 Types of Data. 225 One-Hot
Encoding. 226 Normalizing and Standardizing.227 Normalization.228 Standardization. 229 Remembering the Transformation. 230 Types of Transformations.231 Slice Processing. 232 Samplewise Processing.232 Featurewise Processing.233 Elementwise Processing.234 Inverse Transformations. 234 Information Leakage in Cross-Validation. 239 Shrinking the Dataset. 242 Feature
Selection. 243 Dimensionality Reduction. 243 Principal Component Analysis. 244 PCA for Simple Images.250 PCA for Real Images. 255 Summary. 260 XIV Contents in Detail
11 CLASSIFIERS 263 Types of Classifiers.264 k-Nearest Neighbors. 264 Decision Trees.269 Introduction to Trees. 269 Using Decision Trees. 271 Overfitting Trees. 275 Splitting Nodes. 280 Support Vector Machines. 282 The Basic Algorithm. 282 The SVM Kernel Trick. 287 Naive Bayes. 290 Comparing Classifiers.295
Summary.296 12 ENSEMBLES 297 Voting.298 Ensembles of Decision Trees. 299 Bagging. 299 Random Forests. 301 Extra Trees. 302 Boosting. 302 Summary.309 PART III: DEEP LEARNING BASICS 13 NEURAL NETWORKS 311 313 Real Neurons. 314 Artificial Neurons. 315 The Perceptron.315 Modern Artificial
Neurons.317 Drawing the Neurons. 319 Feed-Forward Networks.322 Neural Network Graphs.323 Initializing the Weights. 325 Deep Networks.326 Fully Connected Layers. 328 Tensors. 328 Preventing Network Collapse. 329 Activation Functions.331 Straight-Line Functions.331 Step Functions.333 Piecewise Linear
Functions.336 Smooth Functions.339 Contents in Detail
Activation Function Gallery.344 Comparing Activation Functions.344 Softmax. 345 Summary. 348 14 BACKPROPAGATION 351 A High-Level Overview of Training .352 Punishing Error.352 A Slow Way to Learn. 354 Gradient Descent.355 Getting Started.356 Backprop on a Tiny Neural Network.358 Finding Deltas for the Output Neurons. 360 Using Deltas to Change Weights. 366 Other Neuron Deltas. 368
Backprop on a Larger Network. 372 The Learning Rate. 376 Building a Binary Classifier.378 Picking a Learning Rate.379 An Even Smaller Learning Rate. 383 Summary. 386 15 OPTIMIZERS 387 Error as a 2D Curve.388 Adjusting the Learning Rate.389 Constant-Sized Updates.391 Changing the Learning Rate over Time. 396 Decay Schedules. 398 Updating Strategies.400 Batch Gradient
Descent. 401 Stochastic Gradient Descent . 403 Mini-Batch Gradient Descent. 405 Gradient Descent Variations. 407 Momentum.408 Nesterov Momentum. 414 Adag rad.417 Adadelta and RMSprop. 418 Adam.420 Choosing an Optimizer.421 Regularization.422 Dropout. 422 Batchnorm.424
Summary. 425 XVI Contents in Detail
PART IV: BEYOND THE BASICS 16 CONVOLUTIONAL NEURAL NETWORKS 427 429 Introducing Convolution. 430 Detecting Yellow. 431 Weight Sharing. 433 Larger Filters. 434 Filters and Features.437 Padding. 440 Multidimensional Convolution. 443 Multiple Filters. 444 Convolution Layers. 446 1 D Convolution. 446 1x1 Convolutions . 447 Changing Output Size.449
Pooling. 449 Striding. 453 Transposed Convolution. 457 Hierarchies of Filters.461 Simplifying Assumptions. 461 Finding Face Masks. 462 Finding Eyes, Noses, and Mouths. 465 Applying Our Filters. 467 Summary. 472 17 CONVNETS IN PRACTICE 473 Categorizing Handwritten Digits. 473 VGG16. 478 Visualizing Filters, Part 1. 481 Visualizing Filters, Part
2. 487 Adversaries.491 Summary. 493 18 AUTOENCODERS 495 Introduction to Encoding. 496 Lossless and Lossy Encoding. 496 Blending Representations. 498 The Simplest Autoencoder. 500 A Better Autoencoder. 505 Exploring the Autoencoder.508 A Closer Look at the Latent Variables. 508 The Parameter Space. 508 Blending Latent Variables. 513 Predicting from Novel
Input. 515 Convolutional Autoencoders. 516 Blending Latent Variables. 517 Predicting from Novel Input. 519 Contents in Detail
Denoting. 519 Variational Autoencoders. 521 Distribution of Latent Variables.522 Variational Autoencoder Structure. 523 Exploring the VAE. 530 Working with the MNIST Samples. 530 Working with Two Latent Variables.533 Producing New Input. 535 Summary. 538 19 RECURRENT NEURAL NETWORKS 539 Working with Language.540 Common Natural Language Processing Tasks. 540 Transforming Text into Numbers. 541 Fine-Tuning and DownstreamNetworks ;. 542 Fully Connected
Prediction. 542 Testing Our Network. 543 Why Our Network Failed.546 Recurrent Neural Networks. 548 Introducing State. 548 Rolling Up Our Diagram. 549 Recurrent Cells in Action. 552 Training a Recurrent Neural Network. 552 Long Short-Term Memory andGated Recurrent Networks.553 Using Recurrent Neural Networks. 554 Working with Sunspot Data. 554 Generating Text. 555 Different Architectures.557
Seq2Seq. 561 Summary.564 20 ATTENTION AND TRANSFORMERS 565 Embedding.566 Embedding Words.569 ELMo. 571 Attention. 574 A Motivating Analogy. 574 Self-Attention. 576 Q/KV Attention. 579 Multi-Head Attention. 580 Layer Icons.581 Transformers. 581 Skip
Connections. 582 Norm-Add.583 Positional Encoding. !. 584 Assembling a Transformer.586 Transformers in Action. 589 XVIII Contents in Detail
BERT and GPT-2.590 BERT. 590 GPT-2.593 Generators Discussion.596 Data Poisoning.598 Summary. 599 21 REINFORCEMENT LEARNING 601 Basic Ideas.602 Learning a New Game. 603 The Structure of Reinforcement Learning.605 Step 1 : The Agent Selects an Action. 605 Step 2: The Environment Responds.606 Step 3: The Agent Updates Itself. 607 Back to the Big
Picture.608 Understanding Rewards. 608 Flippers. 614 L-Learning. 616 The Basics.616 The L-Learning Algorithm. 619 Testing Our Algorithm. 621 Handling Unpredictability.624 Q-Learning.626 Q-Values and Updates.627 Q-Learning Policy.630 Putting It All Together. 632 The Elephant in the Room. 633
Q-learning in Action. 634 SARSA. 638 The Algorithm. 639 SARSA in Action. 642 Comparing Q-Learning and SARSA.644 The Big Picture. 646 Summary. 648 22 GENERATIVE ADVERSARIAL NETWORKS 649 Forging Money.650 Learning from Experience. 652 Forging with Neural Networks.653 A Learning Round.655 Why Adversarial?.656 Implementing
GANs. 657 The Discriminator.657 The Generator.658 Training the GAN.658 GANs in Action.660 Building a Discriminator and Generator . 662 Training Our Network.664 Testing Our Network. 665 Contents in Detail XIX
DCGANs.666 Challenges. 669 Using Big Samples. 670 Modal Collapse. 671 Training with Generated Data.671 Summary.673 23 CREATIVE APPLICATIONS 675 Deep Dreaming.675 Stimulating Filters.676 Running Deep Dreaming. 678 Neural Style Transfer.680 Representing Style.680 Representing
Content.683 Style and Content Together.683 Running Style Transfer. 685 Generating More of This Book.688 Summary.690 Final Thoughts. 690 REFERENCES 693 IMAGE CREDITS 717 INDEX 721 XX Contents in Detail |
| adam_txt |
BRIEF CONTENTS Acknowledgments. xxi Introduction. xxiii PART I: FOUNDATIONAL IDEAS.1 Chapter 1 : An Overview of Machine Learning.3 Chapter 2: Essential Statistics. 15 Chapter 3: Measuring Performance. 47 Chapter 4: Bayes' Rule.83 Chapter 5: Curves and Surfaces. 117 Chapter 6: Information Theory.133 PART II: BASIC MACHINE LEARNING. 153 Chapter 7: Classification.155 Chapter 8: Training and Testing. 181 Chapter 9: Overfitting and
Underfitting. 195 Chapter 10: Data Preparation. 221 Chapter 11 : Classifiers. 263 Chapter 12: Ensembles. 297 PART III: DEEP LEARNING BASICS. 311 Chapter 13: Neural Networks. 313 Chapter 14: Backpropagation. 351 Chapter 15: Optimizers 387
PART IV: BEYOND THE BASICS.427 Chapter 16: Convolutional Neural Networks.429 Chapter 17: Convnets in Practice. 473 Chapter 18: Autoencoders.495 Chapter 19: Recurrent Neural Networks.539 Chapter 20: Attention and Transformers.565 Chapter 21 : Reinforcement Learning. 601 Chapter 22: Generative Adversarial Networks. 649 Chapter 23: Creative Applications. 675 References. 693 Image Credits.717 Index.721 X Brief Contents
CONTENTS IN DETAIL ACKNOWLEDGMENTS INTRODUCTION xxi xxiii Who This Book Is For.xxiv This Book Has No Math and No Code.xxv There Is Code, If You Want It. xxv The Figures Are Available, Too!. xxv Errata.xxvi About This Book. xxvi Part I: Foundational Ideas.xxvi Part II: Basic Machine Learning. xxvii Part III: Deep Learning Basics. xxvii Part IV: Deep Beyond the Basics.xxvii Final Words. xxviii PART I: FOUNDATIONAL IDEAS 1 1 AN OVERVIEW OF MACHINELEARNING 3 Expert
Systems.4 Supervised Learning. 6 Unsupervised Learning.8 Reinforcement Learning . 9 Deep Learning. 10 Summary. 13 2 ESSENTIAL STATISTICS 15 Describing Randomness. 16 Random Variables and Probability Distributions . 17 Some Common Distributions.21 Continuous Distributions.21 Discrete Distributions. 26 Collections of Random Values.28 Expected
Value. 28 Dependence.29 Independent and Identically Distributed Variables.29 Sampling and Replacement. 29 Selection with Replacement.30 Selection Without Replacement. 30 Bootstrapping. 31 Covariance and Correlation. 35 Covariance.36 Correlation. 37
Statistics Don't Tell Us Everything.40 High-Dimensional Spaces. 42 Summary. 44 3 MEASURING PERFORMANCE 47 Different Types of Probability.48 Dart Throwing.48 Simple Probability. 50 Conditional Probability.50 Joint Probability.53 Marginal Probability.55 Measuring Correctness. 56 Classifying Samples.57 The Confusion Matrix. 60 Characterizing Incorrect
Predictions.61 Measuring Correct and Incorrect. 63 Accuracy. 64 Precision. 65 Recall. 66 Precision-Recall Tradeoff.67 Misleading Measures. 69 fl Score.71 About These Terms. 72 Other Measures.72 Constructing a Confusion Matrix Correctly.74 Summary.81 4 BAYES' RULE 83 Frequentisi and Bayesian Probability. 84 The
Frequentisi Approach.84 The Bayesian Approach. 85 Frequentists vs. Bayesians. 85 Frequentisi Coin Flipping. 86 Bayesian Coin Flipping. 87 A Motivating Example. 87 Picturing the Coin Probabilities. 88 Expressing Coin Flips as Probabilities.90 Bayes' Rule.94 Discussion of Bayes' Rule.95 Bayes' Rule and Confusion Matrices. 97 Repeating Bayes'Rule. 101 The Posterior-Prior Loop. 102 The Bayes Loop in
Action. 103 Multiple Hypotheses. 109 Summary. 115 XH Contents in Detail
5 CURVES AND SURFACES 117 The Nature of Functions. The Derivative. Maximums and Minimums. Tangent Lines. Finding Minimums and Maximums with Derivatives. The Gradient. Water, Gravity, and the Gradient. Finding Maximums and Minimums with Gradients. Saddle Points. Summary. 118 119 119 122 125 126 127 128 130 131 6 INFORMATION THEORY 133 Surprise and Context. Understanding Surprise. Unpacking Context.
Measuring Information. Adaptive Codes. Speaking Morse. Customizing Morse Code. Entropy. Cross Entropy. Two Adaptive Codes. Using the Codes. Cross Entropy in Practice. Kullback-Leibler Divergence. Summary. PART II: BASIC MACHINE LEARNING 134 134 135 136 137 138 141 143 145 146 148 150 151 152 153 7 CLASSIFICATION 155 Two-Dimensional Binary Classification. 2D Multiclass
Classification. Multiclass Classification. One-Versus-Rest. One-Versus-One. Clustering. The Curse of Dimensionality. Dimensionality and Density. High-Dimensional Weirdness. Summary. 156 160 161 161 163 166 168 169 175 179 Contents in Detail
8 TRAINING AND TESTING 181 Training. Testing the Performance. Test Data. Validation Data. Cross-Validation. k-Fold Cross-Validation. Summary. 9 OVERFITTING AND UNDERFITTING 182 183 1 86 187 190 192 194 195 Finding a Good Fit. 196 Overfitting. 196 Underfitting. 197 Detecting and Addressing Overfitting. 197 Early
Stopping.202 Regularization.203 Bias and Variance. 204 Matching the Underlying Data.205 High Bias, Low Variance. 207 Low Bias, High Variance. 209 Comparing Curves.210 Fitting a Line with Bayes' Rule. 212 Summary. 219 10 DATA PREPARATION 221 Basic Data Cleaning.222 The Importance of Consistency. 223 Types of Data. 225 One-Hot
Encoding. 226 Normalizing and Standardizing.227 Normalization.228 Standardization. 229 Remembering the Transformation. 230 Types of Transformations.231 Slice Processing. 232 Samplewise Processing.232 Featurewise Processing.233 Elementwise Processing.234 Inverse Transformations. 234 Information Leakage in Cross-Validation. 239 Shrinking the Dataset. 242 Feature
Selection. 243 Dimensionality Reduction. 243 Principal Component Analysis. 244 PCA for Simple Images.250 PCA for Real Images. 255 Summary. 260 XIV Contents in Detail
11 CLASSIFIERS 263 Types of Classifiers.264 k-Nearest Neighbors. 264 Decision Trees.269 Introduction to Trees. 269 Using Decision Trees. 271 Overfitting Trees. 275 Splitting Nodes. 280 Support Vector Machines. 282 The Basic Algorithm. 282 The SVM Kernel Trick. 287 Naive Bayes. 290 Comparing Classifiers.295
Summary.296 12 ENSEMBLES 297 Voting.298 Ensembles of Decision Trees. 299 Bagging. 299 Random Forests. 301 Extra Trees. 302 Boosting. 302 Summary.309 PART III: DEEP LEARNING BASICS 13 NEURAL NETWORKS 311 313 Real Neurons. 314 Artificial Neurons. 315 The Perceptron.315 Modern Artificial
Neurons.317 Drawing the Neurons. 319 Feed-Forward Networks.322 Neural Network Graphs.323 Initializing the Weights. 325 Deep Networks.326 Fully Connected Layers. 328 Tensors. 328 Preventing Network Collapse. 329 Activation Functions.331 Straight-Line Functions.331 Step Functions.333 Piecewise Linear
Functions.336 Smooth Functions.339 Contents in Detail
Activation Function Gallery.344 Comparing Activation Functions.344 Softmax. 345 Summary. 348 14 BACKPROPAGATION 351 A High-Level Overview of Training .352 Punishing Error.352 A Slow Way to Learn. 354 Gradient Descent.355 Getting Started.356 Backprop on a Tiny Neural Network.358 Finding Deltas for the Output Neurons. 360 Using Deltas to Change Weights. 366 Other Neuron Deltas. 368
Backprop on a Larger Network. 372 The Learning Rate. 376 Building a Binary Classifier.378 Picking a Learning Rate.379 An Even Smaller Learning Rate. 383 Summary. 386 15 OPTIMIZERS 387 Error as a 2D Curve.388 Adjusting the Learning Rate.389 Constant-Sized Updates.391 Changing the Learning Rate over Time. 396 Decay Schedules. 398 Updating Strategies.400 Batch Gradient
Descent. 401 Stochastic Gradient Descent . 403 Mini-Batch Gradient Descent. 405 Gradient Descent Variations. 407 Momentum.408 Nesterov Momentum. 414 Adag rad.417 Adadelta and RMSprop. 418 Adam.420 Choosing an Optimizer.421 Regularization.422 Dropout. 422 Batchnorm.424
Summary. 425 XVI Contents in Detail
PART IV: BEYOND THE BASICS 16 CONVOLUTIONAL NEURAL NETWORKS 427 429 Introducing Convolution. 430 Detecting Yellow. 431 Weight Sharing. 433 Larger Filters. 434 Filters and Features.437 Padding. 440 Multidimensional Convolution. 443 Multiple Filters. 444 Convolution Layers. 446 1 D Convolution. 446 1x1 Convolutions . 447 Changing Output Size.449
Pooling. 449 Striding. 453 Transposed Convolution. 457 Hierarchies of Filters.461 Simplifying Assumptions. 461 Finding Face Masks. 462 Finding Eyes, Noses, and Mouths. 465 Applying Our Filters. 467 Summary. 472 17 CONVNETS IN PRACTICE 473 Categorizing Handwritten Digits. 473 VGG16. 478 Visualizing Filters, Part 1. 481 Visualizing Filters, Part
2. 487 Adversaries.491 Summary. 493 18 AUTOENCODERS 495 Introduction to Encoding. 496 Lossless and Lossy Encoding. 496 Blending Representations. 498 The Simplest Autoencoder. 500 A Better Autoencoder. 505 Exploring the Autoencoder.508 A Closer Look at the Latent Variables. 508 The Parameter Space. 508 Blending Latent Variables. 513 Predicting from Novel
Input. 515 Convolutional Autoencoders. 516 Blending Latent Variables. 517 Predicting from Novel Input. 519 Contents in Detail
Denoting. 519 Variational Autoencoders. 521 Distribution of Latent Variables.522 Variational Autoencoder Structure. 523 Exploring the VAE. 530 Working with the MNIST Samples. 530 Working with Two Latent Variables.533 Producing New Input. 535 Summary. 538 19 RECURRENT NEURAL NETWORKS 539 Working with Language.540 Common Natural Language Processing Tasks. 540 Transforming Text into Numbers. 541 Fine-Tuning and DownstreamNetworks ;. 542 Fully Connected
Prediction. 542 Testing Our Network. 543 Why Our Network Failed.546 Recurrent Neural Networks. 548 Introducing State. 548 Rolling Up Our Diagram. 549 Recurrent Cells in Action. 552 Training a Recurrent Neural Network. 552 Long Short-Term Memory andGated Recurrent Networks.553 Using Recurrent Neural Networks. 554 Working with Sunspot Data. 554 Generating Text. 555 Different Architectures.557
Seq2Seq. 561 Summary.564 20 ATTENTION AND TRANSFORMERS 565 Embedding.566 Embedding Words.569 ELMo. 571 Attention. 574 A Motivating Analogy. 574 Self-Attention. 576 Q/KV Attention. 579 Multi-Head Attention. 580 Layer Icons.581 Transformers. 581 Skip
Connections. 582 Norm-Add.583 Positional Encoding. !. 584 Assembling a Transformer.586 Transformers in Action. 589 XVIII Contents in Detail
BERT and GPT-2.590 BERT. 590 GPT-2.593 Generators Discussion.596 Data Poisoning.598 Summary. 599 21 REINFORCEMENT LEARNING 601 Basic Ideas.602 Learning a New Game. 603 The Structure of Reinforcement Learning.605 Step 1 : The Agent Selects an Action. 605 Step 2: The Environment Responds.606 Step 3: The Agent Updates Itself. 607 Back to the Big
Picture.608 Understanding Rewards. 608 Flippers. 614 L-Learning. 616 The Basics.616 The L-Learning Algorithm. 619 Testing Our Algorithm. 621 Handling Unpredictability.624 Q-Learning.626 Q-Values and Updates.627 Q-Learning Policy.630 Putting It All Together. 632 The Elephant in the Room. 633
Q-learning in Action. 634 SARSA. 638 The Algorithm. 639 SARSA in Action. 642 Comparing Q-Learning and SARSA.644 The Big Picture. 646 Summary. 648 22 GENERATIVE ADVERSARIAL NETWORKS 649 Forging Money.650 Learning from Experience. 652 Forging with Neural Networks.653 A Learning Round.655 Why Adversarial?.656 Implementing
GANs. 657 The Discriminator.657 The Generator.658 Training the GAN.658 GANs in Action.660 Building a Discriminator and Generator . 662 Training Our Network.664 Testing Our Network. 665 Contents in Detail XIX
DCGANs.666 Challenges. 669 Using Big Samples. 670 Modal Collapse. 671 Training with Generated Data.671 Summary.673 23 CREATIVE APPLICATIONS 675 Deep Dreaming.675 Stimulating Filters.676 Running Deep Dreaming. 678 Neural Style Transfer.680 Representing Style.680 Representing
Content.683 Style and Content Together.683 Running Style Transfer. 685 Generating More of This Book.688 Summary.690 Final Thoughts. 690 REFERENCES 693 IMAGE CREDITS 717 INDEX 721 XX Contents in Detail |
| any_adam_object | 1 |
| any_adam_object_boolean | 1 |
| author | Glassner, Andrew S. 1960- |
| author_GND | (DE-588)13836043X |
| author_facet | Glassner, Andrew S. 1960- |
| author_role | aut |
| author_sort | Glassner, Andrew S. 1960- |
| author_variant | a s g as asg |
| building | Verbundindex |
| bvnumber | BV047403729 |
| classification_rvk | ST 302 ST 301 ST 300 |
| contents | Part I: Foundational ideas -- An overview of machine learning -- Essential statistics -- Measuring performance -- Bayes' rule -- Curves and surfaces -- Information theory -- Part II: Basic machine learning -- Classification -- Training and testing -- Overfitting and underfitting -- Data preparation -- Classifiers -- Ensembles -- Part III: Deep learning basics -- Neural networks -- Backpropagation -- Optimizers -- Part IV: Beyond the basics -- Convolutional neural networks -- Convnets in practice -- Autoencoders -- Recurrent neural networks -- Attention and transformers -- Reinforcement learning -- Generative adversarial networks -- Creative applications |
| ctrlnum | (OCoLC)1263166253 (DE-599)BVBBV047403729 |
| discipline | Informatik |
| discipline_str_mv | Informatik |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>00000nam a22000008c 4500</leader><controlfield tag="001">BV047403729</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20250116</controlfield><controlfield tag="007">t|</controlfield><controlfield tag="008">210805s2021 xx a||| b||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781718500723</subfield><subfield code="9">978-1-7185-0072-3</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1263166253</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV047403729</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-739</subfield><subfield code="a">DE-573</subfield><subfield code="a">DE-83</subfield><subfield code="a">DE-522</subfield><subfield code="a">DE-Aug4</subfield><subfield code="a">DE-92</subfield><subfield code="a">DE-1043</subfield><subfield code="a">DE-858</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 302</subfield><subfield code="0">(DE-625)143652:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 301</subfield><subfield code="0">(DE-625)143651:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 300</subfield><subfield code="0">(DE-625)143650:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">68T05</subfield><subfield code="2">msc</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Glassner, Andrew S.</subfield><subfield code="d">1960-</subfield><subfield code="0">(DE-588)13836043X</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Deep learning</subfield><subfield code="b">a visual approach</subfield><subfield code="c">Andrew Glassner</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">San Francisco, CA</subfield><subfield code="b">No Starch Press, Inc.</subfield><subfield code="c">[2021]</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">xxviii, 736 Seiten</subfield><subfield code="b">Illustrationen, Diagramme</subfield><subfield code="c">24 cm</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="505" ind1="8" ind2=" "><subfield code="a">Part I: Foundational ideas -- An overview of machine learning -- Essential statistics -- Measuring performance -- Bayes' rule -- Curves and surfaces -- Information theory -- Part II: Basic machine learning -- Classification -- Training and testing -- Overfitting and underfitting -- Data preparation -- Classifiers -- Ensembles -- Part III: Deep learning basics -- Neural networks -- Backpropagation -- Optimizers -- Part IV: Beyond the basics -- Convolutional neural networks -- Convnets in practice -- Autoencoders -- Recurrent neural networks -- Attention and transformers -- Reinforcement learning -- Generative adversarial networks -- Creative applications</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">"A practical, thorough introduction to deep learning, without the usage of advanced math or programming. Covers topics such as image classification, text generation, and the machine learning techniques that are the basis of modern AI"--</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Deep Learning</subfield><subfield code="0">(DE-588)1135597375</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Machine learning</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Neural networks (Computer science)</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Artificial intelligence</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Neural networks (Computer science)</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Machine learning</subfield></datafield><datafield tag="653" ind1=" " ind2="6"><subfield code="a">Handbooks and manuals</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Deep Learning</subfield><subfield code="0">(DE-588)1135597375</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Online version</subfield><subfield code="a">Glassner, Andrew</subfield><subfield code="t">Deep learning</subfield><subfield code="d">San Francisco, CA : No Starch Press, Inc., [2021]</subfield><subfield code="z">9781718500730</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">Digitalisierung UB Passau - ADAM Catalogue Enrichment</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=032804748&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="943" ind1="1" ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-032804748</subfield></datafield></record></collection> |
| id | DE-604.BV047403729 |
| illustrated | Illustrated |
| index_date | 2024-07-03T17:53:29Z |
| indexdate | 2025-02-13T09:00:44Z |
| institution | BVB |
| isbn | 9781718500723 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-032804748 |
| oclc_num | 1263166253 |
| open_access_boolean | |
| owner | DE-739 DE-573 DE-83 DE-522 DE-Aug4 DE-92 DE-1043 DE-858 |
| owner_facet | DE-739 DE-573 DE-83 DE-522 DE-Aug4 DE-92 DE-1043 DE-858 |
| physical | xxviii, 736 Seiten Illustrationen, Diagramme 24 cm |
| publishDate | 2021 |
| publishDateSearch | 2021 |
| publishDateSort | 2021 |
| publisher | No Starch Press, Inc. |
| record_format | marc |
| spelling | Glassner, Andrew S. 1960- (DE-588)13836043X aut Deep learning a visual approach Andrew Glassner San Francisco, CA No Starch Press, Inc. [2021] xxviii, 736 Seiten Illustrationen, Diagramme 24 cm txt rdacontent n rdamedia nc rdacarrier Part I: Foundational ideas -- An overview of machine learning -- Essential statistics -- Measuring performance -- Bayes' rule -- Curves and surfaces -- Information theory -- Part II: Basic machine learning -- Classification -- Training and testing -- Overfitting and underfitting -- Data preparation -- Classifiers -- Ensembles -- Part III: Deep learning basics -- Neural networks -- Backpropagation -- Optimizers -- Part IV: Beyond the basics -- Convolutional neural networks -- Convnets in practice -- Autoencoders -- Recurrent neural networks -- Attention and transformers -- Reinforcement learning -- Generative adversarial networks -- Creative applications "A practical, thorough introduction to deep learning, without the usage of advanced math or programming. Covers topics such as image classification, text generation, and the machine learning techniques that are the basis of modern AI"-- Deep Learning (DE-588)1135597375 gnd rswk-swf Maschinelles Lernen (DE-588)4193754-5 gnd rswk-swf Machine learning Neural networks (Computer science) Artificial intelligence Handbooks and manuals Deep Learning (DE-588)1135597375 s Maschinelles Lernen (DE-588)4193754-5 s DE-604 Online version Glassner, Andrew Deep learning San Francisco, CA : No Starch Press, Inc., [2021] 9781718500730 Digitalisierung UB Passau - ADAM Catalogue Enrichment application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=032804748&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
| spellingShingle | Glassner, Andrew S. 1960- Deep learning a visual approach Part I: Foundational ideas -- An overview of machine learning -- Essential statistics -- Measuring performance -- Bayes' rule -- Curves and surfaces -- Information theory -- Part II: Basic machine learning -- Classification -- Training and testing -- Overfitting and underfitting -- Data preparation -- Classifiers -- Ensembles -- Part III: Deep learning basics -- Neural networks -- Backpropagation -- Optimizers -- Part IV: Beyond the basics -- Convolutional neural networks -- Convnets in practice -- Autoencoders -- Recurrent neural networks -- Attention and transformers -- Reinforcement learning -- Generative adversarial networks -- Creative applications Deep Learning (DE-588)1135597375 gnd Maschinelles Lernen (DE-588)4193754-5 gnd |
| subject_GND | (DE-588)1135597375 (DE-588)4193754-5 |
| title | Deep learning a visual approach |
| title_auth | Deep learning a visual approach |
| title_exact_search | Deep learning a visual approach |
| title_exact_search_txtP | Deep learning a visual approach |
| title_full | Deep learning a visual approach Andrew Glassner |
| title_fullStr | Deep learning a visual approach Andrew Glassner |
| title_full_unstemmed | Deep learning a visual approach Andrew Glassner |
| title_short | Deep learning |
| title_sort | deep learning a visual approach |
| title_sub | a visual approach |
| topic | Deep Learning (DE-588)1135597375 gnd Maschinelles Lernen (DE-588)4193754-5 gnd |
| topic_facet | Deep Learning Maschinelles Lernen |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=032804748&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT glassnerandrews deeplearningavisualapproach |