Deep Learning with Applications Using Python Chatbots and Face, Object, and Speech Recognition With TensorFlow and Keras

Table of Contents......Page 4
Foreword by Tarry Singh......Page 10
About the Author......Page 13
About the Technical Reviewer......Page 14
Chapter 1: Basics of TensorFlow......Page 15
 Tensors......Page 16
 Computational Graph and Session......Page 17
 Constants, Placeholders, and Variables......Page 20
 Placeholders......Page 23
 Creating Tensors......Page 26
  Fixed Tensors......Page 27
  Sequence Tensors......Page 28
  Random Tensors......Page 29
 Working on Matrices......Page 30
 Activation Functions......Page 31
  Tangent Hyperbolic and Sigmoid......Page 32
  ReLU and ELU......Page 33
  ReLU6......Page 34
 Loss Functions......Page 36
  Common Loss Functions......Page 37
 Optimizers......Page 39
  Loss Function Examples......Page 40
  Common Optimizers......Page 41
  Metrics Examples......Page 42
  Common Metrics......Page 43
Chapter 2: Understanding and  Working with Keras......Page 45
 Major Steps to Deep Learning Models......Page 46
  Preprocess the Data......Page 47
  Define the Model......Page 48
  Compile the Model......Page 50
  Fit the Model......Page 51
  Prediction......Page 52
  Optional: Summarize the Model......Page 53
 Additional Steps to Improve Keras Models......Page 54
 Keras with TensorFlow......Page 56
 Artificial Neural Network......Page 58
 Multilayer Perceptron......Page 60
 Logistic Regression Model......Page 62
 TensorFlow Steps to Build Models......Page 70
 Linear Regression in TensorFlow......Page 71
 Logistic Regression Model......Page 75
 Multilayer Perceptron in TensorFlow......Page 78
 Log-Linear Model......Page 82
 Keras Neural Network for Linear Regression......Page 84
 Logistic Regression......Page 86
  Keras Neural Network for Logistic Regression......Page 87
  Fashion MNIST Data: Logistic Regression in Keras......Page 90
  Write the Code......Page 93
  Build a Sequential Keras Model......Page 94
 MLPs on MNIST Data (Digit Classification)......Page 97
 MLPs on Randomly Generated Data......Page 101
 Different Layers in a CNN......Page 103
 CNN Architectures......Page 107
 Why TensorFlow for CNN Models?......Page 109
 TensorFlow Code for Building an Image Classifier for MNIST Data......Page 110
 Using a High-Level API for Building CNN Models......Page 116
 Building an Image Classifier for MNIST Data in Keras......Page 117
  Define the Network Structure......Page 119
  Define the Model Architecture......Page 120
 Building an Image Classifier with CIFAR-10 Data......Page 122
  Define the Network Structure......Page 123
 Define the Model Architecture......Page 124
 Pretrained Models......Page 125
 The Concept of RNNs......Page 127
 Modes of LSTM......Page 130
 Sequence Prediction......Page 131
  Sequence Classification......Page 132
  Sequence-to-Sequence Prediction......Page 133
 Time-Series Forecasting with the LSTM Model......Page 134
Chapter 10: Speech to Text and Vice Versa......Page 139
 Speech as Data......Page 140
 Speech Features: Mapping Speech to a Matrix......Page 141
 Spectrograms: Mapping Speech to an Image......Page 143
 Building a Classifier for Speech Recognition Through MFCC Features......Page 144
 Building a Classifier for Speech Recognition Through a Spectrogram......Page 145
  Using PocketSphinx......Page 147
  Using the Google Speech API......Page 148
  Using the Wit.ai API......Page 149
  Using the IBM Speech to Text API......Page 150
  Using the Bing Voice Recognition API......Page 151
  Using SpeechLib......Page 152
  Audio Cutting Code......Page 153
 Cognitive Service Providers......Page 154
  Amazon Cognitive Services......Page 155
 The Future of Speech Analytics......Page 156
Chapter 11: Developing Chatbots......Page 157
 Designs and Functions of Chatbots......Page 158
 Steps for Building a Chatbot......Page 159
   Removing Punctuation Marks......Page 160
   Removing Stop Words......Page 161
    Using Stanford NER......Page 162
    Using MITIE NER (Self-Trained)......Page 163
   Intent Classification......Page 164
    Word Embedding......Page 165
     Term Frequency-Inverse Document Frequency (TF-IDF)......Page 166
    Word2Vec......Page 169
   Building the Response......Page 177
  Chatbot Development Using APIs......Page 178
   Cognitive Services of Microsoft Azure......Page 179
   IBM Watson......Page 180
  Read the User Sentiments and Make the Bot Emotionally Enriching......Page 181
Chapter 12: Face Detection and Recognition......Page 183
 OpenCV......Page 184
  Eigenfaces......Page 185
  LBPH......Page 187
  Fisherfaces......Page 188
 Detecting a Face......Page 189
 Tracking the Face......Page 191
 Face Recognition......Page 194
 Deep Learning–Based Face Recognition......Page 197
  Why Transfer Learning?......Page 200
  Transfer Learning Example......Page 201
  Calculate the Transfer Value......Page 203
 APIs......Page 209
Appendix 1: Keras Functions for  Image Processing......Page 212
Appendix 2: Some of the Top Image Data Sets Available......Page 217
 What Is the DICOM File Format?......Page 220
Index......Page 222