Programming with TensorFlow: Solution for Edge Computing Applications (EAI/Springer Innovations in Communication and Computing)

Description

This practical book provides an end-to-end guide to TensorFlow, the leading open source software library that helps you build and train neural networks for deep learning, Natural Language Processing (NLP), speech recognition, and general predictive analytics. The book provides a hands-on approach to TensorFlow fundamentals for a broad technical audience―from data scientists and engineers to students and researchers. The authors begin by working through some basic examples in TensorFlow before diving deeper into topics such as CNN, RNN, LSTM, and GNN. The book is written for those who want to build powerful, robust, and accurate predictive models with the power of TensorFlow, combined with other open source Python libraries. The authors demonstrate TensorFlow projects on Single Board Computers (SBCs). Preface Acknowledgement Contents Introduction to Tensorflow Package 1 Why Tensorflow for Deep Learning? 2 Installation Guide to Tensorflow 2.1 System Requirement References Tensorflow Basics 1 Hello Tensorflow Program 2 Representation of Vector/Matrix 3 With Session() Vs without Session() 4 Zeros Matrix and Ones Matrix 5 Make Matrix Negative 6 Variables and Constants 7 Variables Concept in Tensorflow 8 Implement Concept of Placeholder 9 Simple Equations Using Tensorflow 10 Simple Operations in Tensorflow References Visualizations 1 Matplotlib in Tensorflow 1.1 Histogram Implementation 1.2 Trigonometric Curves References Regression 1 Regression Model – Simple Linear Equation 2 Linear Regression 3 Logistic Regression 4 Linear Regression by Importing Datasets 5 Logistic Regression by Importing Dataset References Neural Network 1 Inside the Code References Convolutional Neural Network 1 How Does It Work? References Recurrent Neural Network 1 How They Work? 1.1 Backpropagation Through Time (BPTT) 1.2 In the Code 2 Long Short-Term Memory 2.1 LSTM In Keras References Application of Machine Learning and Deep Learning 1 Automobile Industry 2 Climate Change 3 Disaster Management 4 Education 5 Energy 6 Entertainment and Media 6.1 AlphaGo 6.2 Voice Generation 6.3 Music Generation 6.4 Restoring Sounds in Video 6.5 Automatically Writing Wikipedia 6.6 Deep-Fake Detection 6.7 Multi-Agent Systems 6.8 Image Synthesis 6.9 Graphic Generator 7 Finance References Chatbot References PyTorch 1 The Significant Highlights of PyTorch 2 Why We Prefer PyTorch 3 Requirements for Implementing Deep Learning 4 PyTorch Basic Components 4.1 Tensor 4.2 Autograd Module 5 Implement the Neural Network Using PyTorch 6 Difference Between PyTorch and Tensorflow 7 PyTorch for Computer Vision 7.1 Image Classifier 7.2 Image Augmentation in Less Data 8 Sequential Data Models 8.1 LSTM in PyTorch 9 Summary References Pattern Recognition and Machine Learning 1 Kernel Support Vector Machine 1.1 Linear Kernel 1.2 RBF Kernel 1.3 Polynomial Kernel 2 Kernel Ridge Regression 3 Kernel Density Estimator 3.1 Density Estimation 3.2 Constructing a Kernel Density Estimate 3.3 Features of the Algorithm 3.3.1 Bandwidth Selection 3.3.2 Kernels 3.3.3 Heterogeneous Data 3.3.4 Fast Fourier Transform–Based Computations 3.3.5 Tree-Based Computations 3.3.6 Computational Efficiency 4 Dimensionality Reduction with Kernel Principal Component Analysis 5 Hidden Markov Model to Estimate the Behavior of a Person or Animal 6 Factor Analysis 7 Twitter Sentiment Analysis References Programming Tensor Flow with Single Board Computers 1 Introduction 2 CUDA Programming in NVIDIA 3 Prepackaging Inspection Module for Industry 4.0 4 Fish Geopositioning System for Industry 4.0 5 Conclusion References Appendices Appendix 1 Appendix 2 References Data Set Web References References Books Article References Index