Learning Algorithms for Internet of Things: Applying Python Tools to Improve Data Collection Use for System Performance

Table of Contents About the Authors About the Technical Reviewer Acknowledgments Preface Chapter 1: Introduction to Learning Algorithms 1.1 Genetic Algorithms 1.1.1 Identifying Key Terms 1.1.2 Generation Stages 1.1.3 Generation Applications 1.2 Machine Learning 1.3 Deep Learning 1.4 Optimization 1.4.1 Types of Optimizers 1.5 Summary Chapter 2: Python Packages for Learning Algorithms 2.1 Keras 2.1.1 Features of Keras 2.1.2 Keras Ecosystem 2.1.3 Layers in Keras 2.2 TensorFlow 2.2.1 Features of TensorFlow 2.2.2 Modules of TensorFlow 2.3 PyTorch 2.3.1 Features of PyTorch 2.3.2 Libraries in PyTorch 2.3.3 Modules in PyTorch 2.4 SciPy 2.4.1 Features of SciPy 2.4.2 Modules in SciPy 2.5 Theano 2.5.1 Features of Theano 2.5.2 Modules in Theano 2.6 Pandas 2.6.1 Features of Pandas 2.6.2 Modules in Pandas 2.7 Matplotlib 2.7.1 Features of Matplotlib 2.7.2 Modules in Matplotlib 2.8 Scikit-learn 2.8.1 Features of Scikit-learn 2.8.2 Modules in Scikit-learn 2.9 Seaborn 2.9.1 Features of Seaborn 2.9.2 Modules in Seaborn 2.10 OpenCV 2.10.1 Features of OpenCV 2.10.2 Modules in OpenCV 2.11 Summary Chapter 3: Supervised Algorithms 3.1 Introduction 3.2 Regression 3.2.1 Linear Regression 3.2.2 Polynomial Regression 3.2.3 Bayesian Linear Regression 3.2.4 Ridge Regression 3.2.5 Lasso Regression 3.2.6 Case Study with Medical Applications 3.3 Classification 3.3.1 Logistic Regression 3.3.2 Decision Trees 3.3.3 Naïve Bayes 3.3.4 Random Forest 3.3.5 Support Vector Machines 3.3.6 Case Study with Agriculture Chapter 4: Unsupervised Algorithms 4.1 Introduction 4.2 K-Means Clustering 4.3 Hierarchical Clustering 4.4 Principal Component Analysis 4.5 Independent Component Analysis 4.6 Anomaly Detection 4.7 Neural Networks 4.8 Apriori Algorithm 4.9 Singular Value Decomposition (SVD) 4.10 Case Study with Summarization 4.11 Summary Chapter 5: Reinforcement Learning 5.1 Introduction 5.2 Components of Reinforcement Learning 5.3 Types of Reinforcement Learning 5.4 Reinforcement Learning Algorithms 5.4.1 Markov Decision Process 5.4.2 Bellman Equation 5.4.3 Tabular Methods 5.4.4 Dynamic Programming 5.4.5 Monte Carlo Methods 5.4.6 Temporal Difference 5.4.7 N-Step Bootstrapping 5.4.8 Neural Network Methods 5.5 Applications of Reinforcement Learning 5.6 Case Study with Python 5.7 Summary Chapter 6: Artificial Neural Networks for IoT 6.1 Introduction to Artificial Neural Networks (ANNs) 6.2 Architecture of ANN 6.3 Activation Function 6.4 Loss Function 6.5 Types of Artificial Neural Network Architectures 6.5.1 Feed-Forward ANN 6.5.2 Feedback Networks 6.5.3 Unsupervised ANNs 6.6 Summary Chapter 7: Convolutional Neural Networks for IoT 7.1 Introduction 7.2 General Architecture of CNN 7.3 Types of CNNs 7.4 Case Study for Computer Vision 7.5 Summary Chapter 8: RNNs, LSTMs, and GANs 8.1 Introduction 8.2 Recurrent Neural Networks 8.3 Long Short-Term Memory (LSTM) 8.4 Bidirectional LSTM Model 8.5 Generative Adversarial Networks (GANs) 8.6 Application Case Study 8.7 Summary Chapter 9: Optimization Methods 9.1 Introduction 9.2 Gradient Descent 9.3 Batch Gradient Descent 9.4 Stochastic Gradient Descent 9.5 Mini-Batch Gradient Descent 9.6 Adagrad 9.7 RMSProp 9.8 Adadelta 9.9 Momentum 9.10 Nesterov Momentum 9.11 Adam 9.12 Adamax 9.13 SMORMS3 9.14 Summary