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

✍ Scribed by SpringerLink (Online service); Manaswi, Navin Kumar

• Publisher: Apress
• Year: 2018
• Tongue: English
• Leaves: 228
• Edition: 1st ed. 2018
• Category: Library

✦ Synopsis

Explore deep learning applications, such as computer vision, speech recognition, and chatbots, using frameworks such as TensorFlow and Keras. This book helps you to ramp up your practical know-how in a short period of time and focuses you on the domain, models, and algorithms required for deep learning applications.Deep Learning with Applications Using Pythoncovers topics such as chatbots, natural language processing, and face and object recognition. The goal is to equip you with the concepts, techniques, and algorithm implementations needed to create programs capable of performing deep learning.
This book covers convolutional neural networks, recurrent neural networks, and multilayer perceptrons. It also discusses popular APIs such as IBM Watson, Microsoft Azure, and scikit-learn.
What You Will Learn
Work with various deep learning frameworks such as TensorFlow, Keras, and scikit-learn.


Use face recognition and face detection capabilities


Create speech-to-text and text-to-speech functionality


Engage with chatbots using deep learning



Who This Book Is For
Data scientists and developers who want to adapt and build deep learning applications.

✦ Table of Contents

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