AI Applications to Communications and Information Technologies

Ch 1: Overview 1.1 Introduction and Basic Concepts 1.1.1 Machine Learning 1.1.2 Deep Learning 1.1.3 Activation Functions 1.1.4 MLPs 1.1.5 RNNs 1.1.6 CNNs 1.1.7 Comparison 1.2 Learning Methods 1.3 Areas of applicability 1.4 Scope of this text References Glossary Ch 2: Current and evolving applications to Natural Language Processing 2.1 Scope 2.2 Introduction 2.3 Overview of Natural Language Processing and Speech Processing 2.3.1 Feed-forward NN 2.3.2 RNNs 2.3.3 LSTM 2.3.4 Attention 2.3.5 Transformer 2.4 NLP/NLU Basics 2.4.1 Pre-training 2.4.2 NLP/NLG Architectures 2.4.3 Encoder-Decoder Methods 2.4.4 Application of Transformer 2.4.5 Other Approaches 2.5 NLG Basics 2.6 Chatbots References Glossary Chapter 3: Current and evolving applications to Speech Processing 3.1 Scope 3.2 Overview 3.2.1 Traditional Approaches 3.2.2 DNN-based feature extraction 3.3 Noise Cancellation 3.3.1 Approaches 3.3.2 Example of a system supporting noise cancellation 3.4 Training 3.5 Applications to voice interfaces used to control home devices & Digital Assistant Applications 3.6 Attention-based models 3.7 Sentiment Extraction 3.8 End-to-end learning 3.9 Speech Synthesis 3.10 Zero-shot TTS 3.11 VALL-E: Unseen speaker as an acoustic prompt References Glossary Ch 4: Current and evolving applications to Video and Imaging 4.1 Overview 4.2 Convolution process 4.3 CNNs 4.3.1 Nomenclature 4.3.2 Basic Formulation of the CNN layers 4.3.3 Fully convolutional networks (FCN) 4.3.4 Convolutional Autoencoders 4.3.5 R-CNNs, Fast R-CNN, Faster R-CNN 4.4 Imaging Applications 4.4.1 Basic Image Management 4.4.2 Image segmentation and classification 4.4.3 Illustrative examples of a DNN/CNN 4.4.4 Well-known Image classification networks 4.5 Specific application Examples 4.5.1 Semantic segmentation and semantic edge detection 4.5.2 CNN Filtering Process For Video Coding 4.5.3 Virtual clothing 4.5.5 Object Detection Applications 4.5.6 Classifying video data 4.5.7 Example of Training 4.5.8 Example: Image reconstruction is used to remove artifacts 4.5.9 Example: Video Transcoding/Resolution-enhancement 4.5.10 Facial expression recognition 4.5.11 Transformer Architecture for image processing 4.5.12 Example: A GAN Approach/Synthetic Photo 4.5.13 Situational Awareness 4.6 Other models: Diffusion and Consistency Models References Glossary Ch 5: Current and evolving applications to IoT and applications to Smart buildings and energy management 5.1 Introduction 5.1.1 IoT Applications 5.1.2 Smart Cities 5.2 Smart Building ML Applications 5.2.1 Basic Building Elements 5.2.2 Particle Swarm Optimization 5.2.3 Specific ML Example - Qin Model 5.2.3.1 EnergyPlus(TM) 5.3.3.2 Modeling and Simulation 5.2.3.3 Energy Audit Stage 5.2.3.4 Optimization Stage 5.2.3.5 Model Construction 5.2.3.6 EnergyPlus Models 5.2.3.7 Real-Time Control Parameters 5.2.3.8 Neural Networks in the Qin Model (DNN, RNN, CNN) 5.2.3.9 Finding Inefficiency Measures 5.2.3.10 Particle Swarm Optimizer 5.2.3.11 Integration of Particle Swarm Optimization with Neural Networks 5.2.3.12 Deep Reinforcement Learning 5.2.3.13 Deployments 5.3 Example of a Commercial Product - BrainBox 5.3.1 Overview 5.3.2 LSTM Application - technical background 5.3.3 BrainBox Energy Optimization system References Glossary Ch 6: Current and evolving applications to Network Cybersecurity 6.1 Overview 6.2 General Security Requirements 6.3 Corporate resources/intranet Security Requirements 6.3.1 Network And Endsystem Security Testing 6.3.2 Application Security Testing 6.3.3 Compliance Testing 6.4 IoT Security (IoTSec) 6.5 Blockchains 6.6 Zero Trust Environments 6.7 Areas of ML applicability 6.7.1 Example of cyberintrusion detector 6.7.2 Example of Hidden Markov Model (HMM) for intrusion detection 6.7.3 Anomaly Detection Example 6.7.4 Phishing Detection Emails Using Feature Extraction 6.7.5 Example of classifier engine to identify phishing websites 6.7.6 Example of system for data protection 6.7.7 Example of an integrated cybersecurity threat management 6.7.8 Example of a Vulnerability Lifecycle Management System References Glossary Ch 7: Current and evolving applications to Network Management 7.1 Overview 7.2 Examples of Neural Network-Assisted Network Management 7.2.1 Example of NN-based Network Management system (FM) 7.2.2 Example of a model for predictions related to the operation of a telecommunication network (FM) 7.2.3 Prioritizing Network Monitoring Alerts (FM, PM) 7.2.4 System for Recognizing And Addressing Network Alarms (FM) 7.2.5 Load Control Of An Enterprise Network (PM) 7.2.6 Data Reduction To Accelerate Machine Learning For Networking (FM, PM) 7.2.7 Compressing Network Data (PM) 7.2.8 ML Predictor For A Remote Network Management Platform (FM, PM, CM, AM) 7.2.9 Cable Television (CATV) Performance Management system (PM) References Glossary