Deep Learning with Applications Using Python (eBook)

Chatbots and Face, Object, and Speech Recognition With TensorFlow and Keras

Navin Kumar Manaswi (Autor)

eBook Download: PDF

2018 | 1st ed.
XV, 219 Seiten
Apress (Verlag)
978-1-4842-3516-4 (ISBN)

Infos

Build 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 Python covers 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 intermediate and advanced levels of deep learning, including 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.
  
• Build face recognition and face detection capabilities
  
• Create speech-to-text and text-to-speech functionality
  
• Make chatbots using deep learning
  

Who This Book Is For

Data scientists and developers who want to adapt and build deep learning applications.

Navin K Manaswi has been developing AI solutions/products with the use of cutting edge technologies and sciences related to Artificial Intelligence for many years. Having worked for Consulting companies in Malaysia, Singapore and Dubai Smart City project, he has developed a rare skill of delivering end-to-end data science solutions. He has been building solutions for video intelligence, document intelligence and human-like chatbots in his own company. Through this book, he wants to democratize the cognitive computing and services for everyone specially developers, data scientists, software engineers, database engineers, data analysts and CXOs.

---

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 Python covers 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 capabilitiesCreate speech-to-text and text-to-speech functionalityEngage with chatbots using deep learningWho This Book Is ForData scientists and developers who want to adapt and build deep learning applications.

Autor

Navin K Manaswi has been developing AI solutions/products with the use of cutting edge technologies and sciences related to artificial intelligence for many years. Having worked for consulting companies in Malaysia, Singapore and the Dubai Smart City project, he has developed a rare skill of delivering end-to-end data science solutions. He has been building solutions for video intelligence, document intelligence and human-like chatbots in his own company. 

Inhalt

Table of Contents 4
Foreword by Tarry Singh 10
About the Author 13
About the Technical Reviewer 14
Chapter 1: Basics of TensorFlow 15
Tensors 16
Computational Graph and Session 17
Constants, Placeholders, and Variables 20
Placeholders 23
Creating Tensors 26
Fixed Tensors 27
Sequence Tensors 28
Random Tensors 29
Working on Matrices 30
Activation Functions 31
Tangent Hyperbolic and Sigmoid 32
ReLU and ELU 33
ReLU6 34
Loss Functions 36
Loss Function Examples 37
Common Loss Functions 37
Optimizers 39
Loss Function Examples 40
Common Optimizers 41
Metrics 42
Metrics Examples 42
Common Metrics 43
Chapter 2: Understanding and  Working with Keras 45
Major Steps to Deep Learning Models 46
Load Data 47
Preprocess the Data 47
Define the Model 48
Compile the Model 50
Fit the Model 51
Evaluate Model 52
Prediction 52
Save and Reload the Model 53
Optional: Summarize the Model 53
Additional Steps to Improve Keras Models 54
Keras with TensorFlow 56
Chapter 3: Multilayer Perceptron 58
Artificial Neural Network 58
Single-Layer Perceptron 60
Multilayer Perceptron 60
Logistic Regression Model 62
Chapter 4: Regression to MLP in TensorFlow 70
TensorFlow Steps to Build Models 70
Linear Regression in TensorFlow 71
Logistic Regression Model 75
Multilayer Perceptron in TensorFlow 78
Chapter 5: Regression to MLP in Keras 82
Log-Linear Model 82
Keras Neural Network for Linear Regression 84
Logistic Regression 86
scikit-learn for Logistic Regression 87
Keras Neural Network for Logistic Regression 87
Fashion MNIST Data: Logistic Regression in Keras 90
MLPs on the Iris Data 93
Write the Code 93
Build a Sequential Keras Model 94
MLPs on MNIST Data (Digit Classification) 97
MLPs on Randomly Generated Data 101
Chapter 6: Convolutional Neural Networks 103
Different Layers in a CNN 103
CNN Architectures 107
Chapter 7: CNN in TensorFlow 109
Why TensorFlow for CNN Models? 109
TensorFlow Code for Building an Image Classifier for MNIST Data 110
Using a High-Level API for Building CNN Models 116
Chapter 8: CNN in Keras 117
Building an Image Classifier for MNIST Data in Keras 117
Define the Network Structure 119
Define the Model Architecture 120
Building an Image Classifier with CIFAR-10 Data 122
Define the Network Structure 123
Define the Model Architecture 124
Pretrained Models 125
Chapter 9: RNN and LSTM 127
The Concept of RNNs 127
The Concept of LSTM 130
Modes of LSTM 130
Sequence Prediction 131
Sequence Numeric Prediction 132
Sequence Classification 132
Sequence Generation 133
Sequence-to-Sequence Prediction 133
Time-Series Forecasting with the LSTM Model 134
Chapter 10: Speech to Text and Vice Versa 139
Speech-to-Text Conversion 140
Speech as Data 140
Speech Features: Mapping Speech to a Matrix 141
Spectrograms: Mapping Speech to an Image 143
Building a Classifier for Speech Recognition Through MFCC Features 144
Building a Classifier for Speech Recognition Through a Spectrogram 145
Open Source Approaches 147
Examples Using Each API 147
Using PocketSphinx 147
Using the Google Speech API 148
Using the Google Cloud Speech API 149
Using the Wit.ai API 149
Using the Houndify API 150
Using the IBM Speech to Text API 150
Using the Bing Voice Recognition API 151
Text-to-Speech Conversion 152
Using pyttsx 152
Using SAPI 152
Using SpeechLib 152
Audio Cutting Code 153
Cognitive Service Providers 154
Microsoft Azure 155
Amazon Cognitive Services 155
IBM Watson Services 156
The Future of Speech Analytics 156
Chapter 11: Developing Chatbots 157
Why Chatbots? 158
Designs and Functions of Chatbots 158
Steps for Building a Chatbot 159
Preprocessing Text and Messages 160
Tokenization 160
Removing Punctuation Marks 160
Removing Stop Words 161
Named Entity Recognition 162
Using Stanford NER 162
Using MITIE NER (Pretrained) 163
Using MITIE NER (Self-Trained) 163
Intent Classification 164
Word Embedding 165
Count Vector 166
Term Frequency-Inverse Document Frequency (TF-IDF) 166
Word2Vec 169
Building the Response 177
Chatbot Development Using APIs 178
Cognitive Services of Microsoft Azure 179
Amazon Lex 180
IBM Watson 180
Best Practices of Chatbot Development 181
Know the Potential Users 181
Read the User Sentiments and Make the Bot Emotionally Enriching 181
Chapter 12: Face Detection and Recognition 183
Face Detection, Face Recognition, and Face Analysis 184
OpenCV 184
Eigenfaces 185
LBPH 187
Fisherfaces 188
Detecting a Face 189
Tracking the Face 191
Face Recognition 194
Deep Learning–Based Face Recognition 197
Transfer Learning 200
Why Transfer Learning? 200
Transfer Learning Example 201
Calculate the Transfer Value 203
APIs 209
Appendix 1: Keras Functions for Image Processing 212
Appendix 2: Some of the Top Image Data Sets Available 217
Appendix 3: Medical Imaging: DICOM File Format 220
Why DICOM? 220
What Is the DICOM File Format? 220
Index 222

Produkt-Details

• Erscheint lt. Verlag: 4.4.2018
• Zusatzinfo: XV, 219 p. 261 illus.
• Verlagsort: Berkeley
• Sprache: englisch
• Themenwelt: Mathematik / Informatik ► Informatik ► Datenbanken
• Themenwelt: Mathematik / Informatik ► Informatik ► Programmiersprachen / -werkzeuge
• Themenwelt: Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik
• Schlagworte: Deep learning • Keras • Open AI • Open AI Gym • Python • Sci-Kit Learn • tensorflow
• ISBN-10: 1-4842-3516-9 / 1484235169
• ISBN-13: 978-1-4842-3516-4 / 9781484235164