Paperback(2nd ed.)
-
PICK UP IN STORECheck Availability at Nearby Stores
Available within 2 business hours
Related collections and offers
Overview
Summary
Updated with new code, new projects, and new chapters, Machine Learning with TensorFlow, Second Edition gives readers a solid foundation in machine-learning concepts and the TensorFlow library. Written by NASA JPL Deputy CTO and Principal Data Scientist Chris Mattmann, all examples are accompanied by downloadable Jupyter Notebooks for a hands-on experience coding TensorFlow with Python. New and revised content expands coverage of core machine learning algorithms, and advancements in neural networks such as VGG-Face facial identification classifiers and deep speech classifiers.
Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.
About the technology
Supercharge your data analysis with machine learning! ML algorithms automatically improve as they process data, so results get better over time. You don’t have to be a mathematician to use ML: Tools like Google’s TensorFlow library help with complex calculations so you can focus on getting the answers you need.
About the book
Machine Learning with TensorFlow, Second Edition is a fully revised guide to building machine learning models using Python and TensorFlow. You’ll apply core ML concepts to real-world challenges, such as sentiment analysis, text classification, and image recognition. Hands-on examples illustrate neural network techniques for deep speech processing, facial identification, and auto-encoding with CIFAR-10.
What's inside
Machine Learning with TensorFlow
Choosing the best ML approaches
Visualizing algorithms with TensorBoard
Sharing results with collaborators
Running models in Docker
About the reader
Requires intermediate Python skills and knowledge of general algebraic concepts like vectors and matrices. Examples use the super-stable 1.15.x branch of TensorFlow and TensorFlow 2.x.
About the author
Chris Mattmann is the Division Manager of the Artificial Intelligence, Analytics, and Innovation Organization at NASA Jet Propulsion Lab. The first edition of this book was written by Nishant Shukla with Kenneth Fricklas.
Table of Contents
PART 1 - YOUR MACHINE-LEARNING RIG
1 A machine-learning odyssey
2 TensorFlow essentials
PART 2 - CORE LEARNING ALGORITHMS
3 Linear regression and beyond
4 Using regression for call-center volume prediction
5 A gentle introduction to classification
6 Sentiment classification: Large movie-review dataset
7 Automatically clustering data
8 Inferring user activity from Android accelerometer data
9 Hidden Markov models
10 Part-of-speech tagging and word-sense disambiguation
PART 3 - THE NEURAL NETWORK PARADIGM
11 A peek into autoencoders
12 Applying autoencoders: The CIFAR-10 image dataset
13 Reinforcement learning
14 Convolutional neural networks
15 Building a real-world CNN: VGG-Face ad VGG-Face Lite
16 Recurrent neural networks
17 LSTMs and automatic speech recognition
18 Sequence-to-sequence models for chatbots
19 Utility landscape
Product Details
| ISBN-13: | 9781617297717 |
|---|---|
| Publisher: | Manning |
| Publication date: | 02/02/2021 |
| Edition description: | 2nd ed. |
| Pages: | 456 |
| Product dimensions: | 7.38(w) x 9.25(h) x 0.90(d) |
About the Author
Table of Contents
Foreword xvii
Preface xix
Acknowledgments xxi
About this book xxiii
About the author xxviii
About the cover illustration xxix
Part 1 Your Machine-Learning Rig 1
1 A machine-learning odyssey 3
1.1 Machine-learning fundamentals 5
Parameters 7
Learning and inference 8
1.2 Data representation and features 9
1.3 Distance metrics 15
1.4 Types of learning 17
Supervised learning 17
Unsupervised learning 19
Reinforcement learning 19
Meta-learning 20
1.5 Tensor Flow 22
1.6 Overview of future chapters 24
2 TensorFlow essentials 27
2.1 Ensuring that TensorFlow works 29
2.2 Representing tensors 30
2.3 Creating operators 33
2.4 Executing operators within sessions 35
2.5 Understanding code as a graph 36
Setting session configurations 38
2.6 Writing code in Jupyter 39
2.7 Using variables 42
2.8 Saving and loading variables 43
2.9 Visualizing data using TensorBoard 45
Implementing a moving average 45
Visualizing the moving average 47
2.10 Putting it all together: The TensorFlow system architecture and API 49
Part 2 Core Learning Algorithms 53
3 Linear regression and beyond 55
3.1 Formal notation 56
How do you know the regression algorithm is working? 58
3.2 Linear regression 60
3.3 Polynomial model 63
3.4 Regularization 65
3.5 Application of linear regression 70
4 Using regression for call-center volume prediction 72
4.1 What is 311? 75
4.2 Cleaning the data for regression 76
4.3 What's in a bell curve? Predicting Gaussian distributions 81
4.4 Training your call prediction regressor 82
4.5 Visualizing the results and plotting the error 83
4.6 Regularization and training test splits 86
5 A gentle introduction to classification 89
5.1 Formal notation 90
5.2 Measuring performance 92
Accuracy 93
Precision and recall 93
Receiver operating characteristic curve 95
5.3 Using lineal' regression for classification 96
5.4 Using logistic regression 100
Solving ID logistic regression 101
Solving 2D regression 104
5.5 Multiclass classifier 107
One-versus-all 108
One-versus-one 108
Softmax regression 108
5.6 Application of classification 112
6 Sentiment classification: Large movie-review dataset 114
6.1 Using the Bag of Words model 116
Applying the Bag of Words model to movie reviews 117
Cleaning all the movie reviews 119
Exploratory data analysis on your Bag of Words 121
6.2 Building a sentiment classifier using logistic regression 122
Setting up the training for your model 123
Performing the training for your model 124
6.3 Making predictions using your sentiment classifier 125
6.4 Measuring the effectiveness of your classifier 129
6.5 Creating the softmax-regression sentiment classifier 132
6.6 Submitting your results to Kaggle 140
7 Automatically clustering data 143
7.1 Traversing files in TensorFlow 144
7.2 Extracting features from audio 146
7.3 Using k-means clustering 151
7.4 Segmenting audio 154
7.5 Clustering with a self-organizing map 156
7.6 Applying clustering 161
8 Inferring user activity from Android accelerometer data 163
8.1 The User Activity from Walking dataset 165
Creating the dataset 167
Computing jerk and extracting the feature vector 168
8.2 Clustering similar participants based on jerk magnitudes 171
8.3 Different classes of user activity for a single participant 174
9 Hidden Markov models 178
9.1 Example of a not-so-inter pre table model 179
9.2 Markov model 180
9.3 Hidden Markov model 182
9.4 Forward algorithm 183
9.5 Viterbi decoding 186
9.6 Uses of HMMs 187
Modeling a video 187
Modeling DNA 188
Modeling an image 188
9.7 Application of HMMs 188
10 Part-of-speech tagging and word-sense disambiguation 190
10.1 Review of HMM example: Rainy or Sunny 192
10.2 PoS tagging 195
The big picture: Training and predicting PoS with HMMs 199
Generating the ambiguity PoS tagged dataset 202
10.3 Algorithms for building the HMM for PoS disambiguation 204
Generating the emission probabilities 208
10.4 Running the HMM and evaluating its output 212
10.5 Getting more training data from the Brown Corpus 215
10.6 Defining error bars and metrics for PoS tagging 221
Part 3 The Neural Network Paradigm 225
11 A peek into autoencoders 227
11.1 Neural networks 228
11.2 Autoencoders 231
11.3 Batch training 235
11.4 Working with images 236
11.5 Application of autoencoders 240
12 Applying autoencoders: The CIFAR-10 image dataset 241
12.1 What is CIFAR-10? 242
Evaluating your CIFAR-10 autoencoder 244
12.2 Autoencoders as classifiers 247
Using the autoencoder as a classifier via loss 250
12.3 Denoising autoencoders 252
12.4 Stacked deep autoencoders 256
13 Reinforcement learning 261
13.1 Formal notions 262
Policy 263
Utility 264
13.2 Applying reinforcement learning 265
13.3 Implementing reinforcement learning 267
13.4 Exploring other applications of reinforcement learning 274
14 Convolutional neural networks 276
14.1 Drawback of neural networks 277
14.2 Convolutional neural networks 278
14.3 Preparing the image 279
Generating filters 282
Convolving-using filters 283
Max pooling 286
14.4 Implementing a CNN in TensorFlow 288
Measuring performance 290
Training the classifier 291
14.5 Tips and tricks to improve performance 292
14.6 Application of CNNs 293
15 Building a real-world CNN: VGG-Face and VGG-Face Lite 294
15.1 Making a real-world CNN architecture for CIFAR-10 297
Loading and preparing the CIFAR-10 image data 298
Performing data augmentation 300
15.2 Building a deeper CNN architecture for CIFAR-10 302
CAW optimizations for increasing learned parameter resilience 306
15.3 Training and applying a better CIFAR-10 CNN 307
15.4 Testing and evaluating your CNN for CIFAR-10 309
CIFAR-10 accuracy results and ROC curves 312
Evaluating the softmax predictions per class 314
15.5 Building VGG-Face for facial recognition 317
Picking a subset of VGG-Face for training VGG-Face Lite 319
TensorFlow's Dataset API and data augmentation 320
Creating a TensorFlow dataset 322
Training using TensorFlow datasets 324
VGG-Face Lite, model and training 325
Training and evaluating VGG-Face Lite 328
Evaluating and predicting with VGG-Face Lite 330
16 Recurrent neural networks 334
16.1 Introduction to RNNs 335
16.2 Implementing a recurrent neural network 336
16.3 Using a predictive model for time-series data 339
16.4 Applying RNNs 342
17 LSTMs and automatic speech recognition 343
17.1 Preparing the LibriSpeech corpus 344
Downloading, cleaning, and preparing LibriSpeech OpenSLR data 345
Converting the audio 346
Generating per-audio transcripts 347
Aggregating audio and transcripts 348
17.2 Using the deep-speech model 349
Preparing the input audio data for deep speech 351
Preparing the text transcripts as character-level numerical data 354
The deep-speech model in TensorFlow 356
Connectionist temporal classification in TensorFlow 360
17.3 Training and evaluating deep speech 361
18 Sequence-to-sequence models for chatbots 365
18.1 Building on classification and RNNs 366
18.2 Understanding seq2seq architecture 368
18.3 Vector representation of symbols 373
18.4 Putting it all together 374
18.5 Gathering dialogue data 382
19 Utility landscape 384
19.1 Preference model 386
19.2 Image embedding 390
19.3 Ranking images 394
What's next 399
Appendix Installation instructions 401
Index 411