Lesson 1: Introduction to Edge Computing and AI
1.1 Defining Edge Computing: Concepts and Architecture
1.2 Why Edge Computing for AI? Benefits and Use Cases
1.3 Challenges of Deploying AI at the Edge
1.4 Overview of IBM’s Edge Computing Portfolio
1.5 The Role of Edge Computing in Video Analytics
1.6 Understanding the Data Lifecycle at the Edge
1.7 Edge vs. Cloud vs. Fog Computing
1.8 Key Industry Drivers for Edge AI
1.9 Course Objectives and Learning Outcomes
1.10 Setting up the Learning Environment
Lesson 2: Core Concepts of IBM Edge Application Manager (IEAM)
2.1 Introduction to IEAM Architecture
2.2 Understanding the Management Hub
2.3 Exploring Edge Nodes and Agents
2.4 The Role of Services and Policies in IEAM
2.5 Service Publishing and Deployment Process
2.6 Policy-Based Autonomy and Management
2.7 Key Features and Capabilities of IEAM
2.8 Comparing IEAM to Other Edge Platforms
2.9 Use Cases for IEAM in AI Scenarios
2.10 Navigating the IEAM User Interface
Lesson 3: Setting up the IEAM Environment
3.1 Prerequisites for Installing IEAM
3.2 Installing the IEAM Management Hub (Hub Cluster)
3.3 Configuring the Management Hub
3.4 Registering Edge Nodes with the Hub
3.5 Understanding Edge Node Prerequisites
3.6 Troubleshooting Installation Issues
3.7 Verifying the IEAM Installation
3.8 Introduction to the hzn Command-Line Tool
3.9 Basic IEAM Configuration and Setup
3.10 Best Practices for Environment Setup
Lesson 4: Developing Edge Services for AI
4.1 Introduction to Edge Service Development
4.2 Choosing the Right Programming Languages and Frameworks
4.3 Containerizing Edge Services (Docker)
4.4 Building Docker Images for the Edge
4.5 Packaging Services for IEAM Deployment
4.6 Understanding Service Dependencies
4.7 Developing Services with AI/ML Frameworks (TensorFlow, PyTorch)
4.8 Integrating Pre-trained Models into Edge Services
4.9 Testing Edge Services Locally
4.10 Introduction to the IEAM Development Workflow
Lesson 5: Publishing and Deploying Services with IEAM
5.1 The Service Publishing Process in IEAM
5.2 Defining Service Metadata and Dependencies
5.3 Using the hzn Tool for Service Publishing
5.4 Understanding Deployment Policies
5.5 Creating and Managing Deployment Policies
5.6 Deploying Services to Edge Nodes via Policy
5.7 Monitoring Service Deployment Status
5.8 Updating and Versioning Edge Services
5.9 Rolling Back Service Deployments
5.10 Troubleshooting Service Deployment Issues
Lesson 6: Advanced Policy Management in IEAM
6.1 Deep Dive into Policy Types (Deployment, Placement, etc.)
6.2 Defining Complex Deployment Policies
6.3 Using Constraints and Properties in Policies
6.4 Policy Conflict Resolution
6.5 Automating Policy Updates
6.6 Managing Policy Lifecycle
6.7 Using Policy for Autonomous Edge Operations
6.8 Policy-Based Updates and Rollouts
6.9 Security Considerations in Policy Management
6.10 Advanced Policy Use Cases
Lesson 7: Integrating AI Models at the Edge
7.1 Edge-Optimized AI Models
7.2 Techniques for Model Compression and Quantization
7.3 Using Edge AI Hardware Accelerators (GPUs, TPUs, NPUs)
7.4 Integrating AI Frameworks (TensorFlow Lite, OpenVINO)
7.5 Deploying Models within Docker Containers
7.6 Model Inference at the Edge
7.7 Managing Model Updates and Versioning
7.8 Evaluating Model Performance at the Edge
7.9 Handling Data Preprocessing at the Edge
7.10 Ethical Considerations for Edge AI
Lesson 8: Video Analytics Fundamentals at the Edge
8.1 Introduction to Video Analytics
8.2 Why Perform Video Analytics at the Edge?
8.3 Video Data Formats and Standards
8.4 Video Stream Processing Techniques
8.5 Object Detection at the Edge
8.6 Object Tracking at the Edge
8.7 Activity Recognition at the Edge
8.8 Facial Recognition Considerations at the Edge
8.9 Challenges of Real-time Video Processing
8.10 Use Cases for Edge Video Analytics
Lesson 9: Implementing Edge Video Analytics with IEAM
9.1 Designing Edge Services for Video Analytics
9.2 Integrating Video Processing Libraries (OpenCV, FFmpeg)
9.3 Using AI Models for Video Analysis (YOLO, SSD)
9.4 Handling Multiple Video Streams at the Edge
9.5 Optimizing Services for Performance on Edge Hardware
9.6 Packaging Video Analytics Services for IEAM
9.7 Deploying Video Analytics Services via Policy
9.8 Monitoring Video Analytics Performance
9.9 Troubleshooting Video Analytics Deployments
9.10 Case Study: Basic Object Detection Deployment
Lesson 10: Data Management and Storage at the Edge
10.1 Challenges of Data Management at the Edge
10.2 Local Data Storage Options on Edge Nodes
10.3 Data Buffering and Caching at the Edge
10.4 Data Synchronization with the Cloud
10.5 Data Security and Privacy at the Edge
10.6 Data Retention Policies
10.7 Using Edge Databases (SQLite, Edge-optimized NoSQL)
10.8 Data Filtering and Aggregation at the Edge
10.9 Handling Disconnected Operations
10.10 Data Management Best Practices
Lesson 11: Edge Node Management and Monitoring
11.1 Monitoring Edge Node Health and Status
11.2 Resource Monitoring (CPU, Memory, Disk)
11.3 Logging and Log Management at the Edge
11.4 Remote Access and Troubleshooting Edge Nodes
11.5 Edge Node Updates and Maintenance
11.6 Managing Edge Node Configurations
11.7 Using IEAM for Node Management
11.8 Integrating with External Monitoring Systems
11.9 Alerting and Notification Strategies
11.10 Capacity Planning for Edge Nodes
Lesson 12: Security in IBM Edge Computing
12.1 Security Threats at the Edge
12.2 Securing Edge Nodes and Devices
12.3 Service and Data Security in IEAM
12.4 Authentication and Authorization Mechanisms
12.5 Data Encryption at Rest and in Transit
12.6 Secure Service Deployment and Updates
12.7 Vulnerability Management at the Edge
12.8 Compliance Requirements for Edge Deployments
12.9 Incident Response at the Edge
12.10 Best Practices for Edge Security
Lesson 13: Advanced Video Analytics Techniques
13.1 Multi-camera Calibration and Stitching
13.2 Person Re-identification at the Edge
13.3 Anomaly Detection in Video Streams
13.4 Pose Estimation and Action Recognition
13.5 Semantic Segmentation in Video
13.6 Using Temporal Information in Video Analysis
13.7 Handling Low-Light or Poor Quality Video
13.8 Video Summarization at the Edge
13.9 Integrating Multiple AI Models for Complex Analysis
13.10 Evaluating Advanced Video Analytics Models
Lesson 14: Optimizing AI Models for Edge Deployment
14.1 Model Pruning and Sparsity
14.2 Quantization Techniques (Post-training and Training-aware)
14.3 Knowledge Distillation
14.4 Neural Architecture Search (NAS) for Edge
14.5 Using Model Compilers (TensorRT, OpenVINO)
14.6 Benchmarking Model Performance on Edge Hardware
14.7 Profiling Model Inference
14.8 Techniques for Reducing Model Latency
14.9 Optimizing Model Throughput
14.10 Continuous Model Optimization
Lesson 15: Integrating External Services with IEAM
15.1 Integrating with Cloud Services (IBM Cloud, AWS, Azure)
15.2 Using APIs to Interact with External Systems
15.3 Data Ingestion from Edge to Cloud
15.4 Sending Insights from Edge to Cloud for Further Analysis
15.5 Integrating with Message Queues (Kafka, MQTT)
15.6 Using Edge Services to Interact with Local Devices
15.7 Service Composition and Orchestration
15.8 Handling Connectivity Issues with External Services
15.9 Security Considerations for External Integrations
15.10 Case Study: Integrating Edge Analytics with a Cloud Dashboard
Lesson 16: Offline and Disconnected Operations
16.1 Designing Services for Disconnected Environments
16.2 Data Buffering and Synchronization Strategies
16.3 Handling Service Updates in Offline Mode
16.4 Autonomous Decision Making at the Edge
16.5 Managing State in Disconnected Services
16.6 Resiliency and Fault Tolerance
16.7 Data Consistency Challenges
16.8 Testing Offline Capabilities
16.9 Recovering from Disconnected Periods
16.10 Use Cases for Offline Edge AI
Lesson 17: Edge AI Model Training and Retraining
17.1 Challenges of Model Training at the Edge
17.2 Federated Learning Concepts
17.3 Implementing Federated Learning with Edge Devices
17.4 Transfer Learning at the Edge
17.5 Using Edge Data for Model Retraining in the Cloud
17.6 Techniques for Data Augmentation at the Edge
17.7 Managing Training Data at the Edge
17.8 Security and Privacy in Edge Training
17.9 Orchestrating Training Workflows
17.10 Evaluating Retrained Models
Lesson 18: Advanced IEAM Features
18.1 Exploring the IEAM Exchange
18.2 Using Patterns for Service Deployment
18.3 Managing Dependencies with the Exchange
18.4 Understanding the IEAM Agent
18.5 Customizing the IEAM Agent
18.6 Using the IEAM API for Automation
18.7 Integrating IEAM with CI/CD Pipelines
18.8 Advanced Troubleshooting Techniques
18.9 IEAM High Availability and Disaster Recovery
18.10 Future Trends in IEAM
Lesson 19: Edge Hardware Considerations for AI and Video
19.1 Types of Edge Hardware (Gateways, Servers, Devices)
19.2 Hardware Requirements for AI Inference
19.3 Hardware Requirements for Video Processing
19.4 Choosing the Right Hardware for Specific Use Cases
19.5 Power Consumption and Thermal Management
19.6 Ruggedized and Industrial Edge Hardware
19.7 Hardware Security Modules (HSMs)
19.8 Evaluating Hardware Performance
19.9 Future Trends in Edge Hardware
19.10 Working with Different Architectures (x86, ARM)
Lesson 20: Deploying and Managing Large-Scale Edge Deployments
20.1 Planning for Scale
20.2 Automating Edge Node Registration
20.3 Managing Thousands of Edge Nodes
20.4 Grouping and Tagging Edge Nodes
20.5 Scalable Service Deployment Strategies
20.6 Monitoring Large-Scale Deployments
20.7 Centralized Management and Orchestration
20.8 Handling Network Variability at Scale
20.9 Cost Optimization in Large Deployments
20.10 Best Practices for Large-Scale Edge Management
Lesson 21: Edge AI for Manufacturing and Industrial Automation
21.1 Use Cases in Manufacturing
21.2 Predictive Maintenance with Edge AI
21.3 Quality Inspection with Edge Video Analytics
21.4 Worker Safety Monitoring
21.5 Optimizing Production Processes
21.6 Integrating with Industrial Protocols (Modbus, OPC UA)
21.7 Data Acquisition from Industrial Sensors
21.8 Real-time Analytics on the Plant Floor
21.9 Security in Industrial Edge Deployments
21.10 Case Study: Anomaly Detection on a Production Line
Lesson 22: Edge AI for Retail and Smart Spaces
22.1 Use Cases in Retail
22.2 Customer Traffic Analysis
22.3 Inventory Monitoring with Video
22.4 Personalized Customer Experiences
22.5 Loss Prevention with Edge Analytics
22.6 Smart Building Management
22.7 Occupancy Monitoring
22.8 Integrating with Retail Systems
22.9 Privacy Considerations in Retail Analytics
22.10 Case Study: Customer Behavior Analysis in a Store
Lesson 23: Edge AI for Healthcare and Life Sciences
23.1 Use Cases in Healthcare
23.2 Remote Patient Monitoring
23.3 Medical Image Analysis at the Edge
23.4 Assisting Medical Staff with AI
23.5 Hospital Operations Optimization
23.6 Data Privacy and HIPAA Compliance
23.7 Integrating with Medical Devices
23.8 Real-time Analysis of Medical Data
23.9 Security in Healthcare Edge Deployments
23.10 Case Study: AI-assisted Diagnosis on Medical Scans
Lesson 24: Edge AI for Smart Cities and Public Safety
24.1 Use Cases in Smart Cities
24.2 Traffic Management and Analysis
24.3 Public Safety and Surveillance
24.4 Environmental Monitoring
24.5 Infrastructure Monitoring
24.6 Integrating with City Infrastructure
24.7 Data Sharing and Collaboration
24.8 Ethical Considerations in Public Safety AI
24.9 Security in Smart City Deployments
24.10 Case Study: Traffic Flow Optimization
Lesson 25: Edge AI for Energy and Utilities
25.1 Use Cases in Energy and Utilities
25.2 Grid Monitoring and Optimization
25.3 Predictive Maintenance for Infrastructure
25.4 Renewable Energy Management
25.5 Asset Monitoring
25.6 Integrating with SCADA Systems
25.7 Data Acquisition from Sensors
25.8 Real-time Analysis of Energy Data
25.9 Security in Energy Edge Deployments
25.10 Case Study: Anomaly Detection in Power Grid Data
Lesson 26: Advanced Troubleshooting and Debugging
26.1 Debugging Edge Services
26.2 Troubleshooting IEAM Deployment Issues
26.3 Analyzing Edge Node Logs and Metrics
26.4 Using IEAM Tools for Diagnostics
26.5 Network Troubleshooting at the Edge
26.6 Debugging AI Model Inference Issues
26.7 Performance Profiling and Optimization
26.8 Handling Hardware-Specific Issues
26.9 Using Remote Debugging Techniques
26.10 Common Edge Computing Pitfalls and Solutions
Lesson 27: Integrating IEAM with Cloud Platforms (IBM Cloud)
27.1 Overview of IBM Cloud Services
27.2 Integrating IEAM with IBM Cloud Kubernetes Service (IKS)
27.3 Using IBM Cloud Object Storage for Edge Data
27.4 Integrating with IBM Cloud Functions (Serverless)
27.5 Using IBM Cloud Databases
27.6 Connecting Edge Data to IBM Cloud Analytics Services
27.7 Managing Cloud-Edge Data Flow
27.8 Security Considerations for Cloud Integration
27.9 Cost Management in Integrated Deployments
27.10 Case Study: Edge-to-Cloud Data Pipeline
Lesson 28: Integrating IEAM with Other Cloud Platforms (AWS, Azure)
28.1 Overview of AWS Edge Services
28.2 Integrating IEAM with AWS IoT Core
28.3 Using AWS S3 for Edge Data
28.4 Integrating with AWS Lambda@Edge
28.5 Overview of Azure Edge Services
28.6 Integrating IEAM with Azure IoT Edge
28.7 Using Azure Blob Storage for Edge Data
28.8 Integrating with Azure Functions
28.9 Comparing Cloud Integration Strategies
28.10 Best Practices for Multi-Cloud Edge
Lesson 29: Edge AI Model Lifecycle Management
29.1 Model Development and Training Workflow
29.2 Model Packaging and Versioning
29.3 Deploying Models to the Edge
29.4 Monitoring Model Performance at the Edge
29.5 Detecting Model Drift
29.6 Retraining and Updating Models
29.7 A/B Testing Edge Models
29.8 Managing Model Repositories
29.9 Automating the Model Lifecycle
29.10 Tools and Platforms for Model Management
Lesson 30: Performance Optimization for Edge AI and Video
30.1 Profiling Edge Services
30.2 Identifying Performance Bottlenecks
30.3 Optimizing Code for Edge Hardware
30.4 Using Asynchronous Processing
30.5 Batching and Parallel Processing
30.6 Memory Management Techniques
30.7 Network Optimization for Edge Communication
30.8 Hardware Acceleration Tuning
30.9 Load Balancing at the Edge
30.10 Continuous Performance Monitoring
Lesson 31: Designing Resilient Edge Architectures
31.1 Understanding Failure Modes at the Edge
31.2 Designing for Disconnected Operations
31.3 Implementing Redundancy and Failover
31.4 Data Replication Strategies
31.5 Service Health Monitoring and Self-Healing
31.6 Handling Network Disruptions
31.7 Power Outage Considerations
31.8 Disaster Recovery Planning for Edge Deployments
31.9 Testing Resilience
31.10 Building Highly Available Edge Systems
Lesson 32: Security Best Practices for Edge AI and Video
32.1 Implementing Least Privilege
32.2 Securely Managing Credentials and Secrets
32.3 Network Segmentation at the Edge
32.4 Using Firewalls and Intrusion Detection
32.5 Secure Boot and Firmware Updates
32.6 Data Encryption and Access Control
32.7 Auditing and Logging Security Events
32.8 Responding to Security Incidents
32.9 Supply Chain Security for Edge Devices
32.10 Advanced Threat Detection at the Edge
Lesson 33: Ethical and Legal Considerations for Edge AI
33.1 Privacy Concerns in Video Analytics
33.2 Data Anonymization and De-identification
33.3 Bias in AI Models and Mitigation Strategies
33.4 Transparency and Explainability of Edge AI
33.5 Regulatory Compliance (GDPR, CCPA, etc.)
33.6 Ethical Guidelines for AI Development
33.7 Responsible Deployment of Edge AI
33.8 Legal Implications of Edge Data
33.9 Consent and Data Usage Policies
33.10 Building Trust in Edge AI Systems
Lesson 34: Future Trends in Edge Computing and AI
34.1 The Rise of TinyML
34.2 Edge-Native Applications
34.3 5G and Edge Computing
34.4 Blockchain at the Edge
34.5 Quantum Computing and the Edge
34.6 AI Explainability (XAI) at the Edge
34.7 Autonomous Edge Systems
34.8 Edge Computing Standards and Interoperability
34.9 The Role of Edge in the Metaverse
34.10 Emerging Edge Hardware and Software
Lesson 35: Hands-on Lab: Building a Custom Edge Service
35.1 Setting up the Development Environment
35.2 Designing the Service Logic
35.3 Implementing the Service Code
35.4 Containerizing the Service
35.5 Testing the Service Locally
35.6 Packaging the Service for IEAM
35.7 Publishing the Service to IEAM
35.8 Creating a Deployment Policy
35.9 Deploying the Service to an Edge Node
35.10 Verifying Service Functionality
Lesson 36: Hands-on Lab: Deploying an Edge Video Analytics Service
36.1 Preparing Video Data
36.2 Integrating a Pre-trained AI Model
36.3 Implementing Video Stream Processing
36.4 Packaging the Video Analytics Service
36.5 Publishing and Deploying the Service
36.6 Monitoring Video Analytics Output
36.7 Optimizing Service Performance
36.8 Troubleshooting Video Analytics Issues
36.9 Analyzing Results and Insights
36.10 Extending the Service with Additional Features
Lesson 37: Hands-on Lab: Advanced IEAM Policy Configuration
37.1 Defining Complex Policy Constraints
37.2 Using Properties for Targeted Deployment
37.3 Implementing Policy-Based Updates
37.4 Managing Policy Conflicts
37.5 Automating Policy Management with the API
37.6 Testing Policy Behavior
37.7 Monitoring Policy Application
37.8 Troubleshooting Policy Issues
37.9 Using Policy for Service Rollouts
37.10 Advanced Policy Use Cases in Practice
Lesson 38: Hands-on Lab: Integrating Edge Data with the Cloud
38.1 Setting up Cloud Services (e.g., IBM Cloud Object Storage, Databases)
38.2 Modifying an Edge Service to Send Data to the Cloud
38.3 Implementing Data Ingestion in the Cloud
38.4 Securing the Edge-to-Cloud Connection
38.5 Monitoring Data Flow
38.6 Handling Connectivity Issues
38.7 Processing Edge Data in the Cloud
38.8 Visualizing Edge Data in a Cloud Dashboard
38.9 Troubleshooting Data Integration Issues
38.10 Exploring Different Cloud Service Integrations
Lesson 39: Real-World Case Studies and Best Practices
39.1 In-depth Analysis of Successful Edge AI Deployments
39.2 Lessons Learned from Real-World Projects
39.3 Identifying Key Success Factors
39.4 Common Challenges and How to Overcome Them
39.5 Best Practices for Designing Edge Solutions
39.6 Best Practices for Deploying and Managing Edge AI
39.7 Best Practices for Securing Edge Deployments
39.8 Evaluating Different Architectural Patterns
39.9 Cost-Benefit Analysis of Edge AI Solutions
39.10 Planning Your Own Edge AI Project
Lesson 40: Course Review and Accreditation Preparation
40.1 Review of Key Concepts and Topics
40.2 Q&A Session
40.3 Practice Questions and Scenarios
40.4 Tips for the Accreditation Exam
40.5 Understanding the Accreditation Process
40.6 Resources for Further Learning
40.7 Building Your Edge Computing Portfolio
40.8 Career Opportunities in Edge AI
40.9 Final Project or Capstone Overview
40.10 Course Wrap-up and Next Steps
Reviews
There are no reviews yet.