Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Introduction to Edge and Agentic AI
- Overview of agentic AI principles and edge computing contexts
- Considerations regarding latency, privacy, and bandwidth
- Comparative analysis of cloud-based versus edge-based agent architectures
Architecting Lightweight Agent Systems
- Deconstructing the agent loop to suit constrained systems
- Employing asynchronous design patterns for efficient computation
- Striking a balance between autonomy and network connectivity
Configuring the Development Environment
- Installing essential Python frameworks for edge AI
- Setting up TensorFlow Lite and PyTorch Mobile
- Establishing test environments on Raspberry Pi or comparable hardware
Executing On-Device Inference
- Converting and quantizing models to facilitate edge deployment
- Performing inference using TensorFlow Lite and ONNX Runtime
- Integrating inference outputs into the agent’s decision-making cycle
Connecting Agents with Hardware and IoT Ecosystems
- Linking sensors, actuators, and IoT modules
- Building local data collection and processing pipelines
- Ensuring offline capability and event-triggered responses
Optimization and System Monitoring
- Tuning performance for low power consumption and high speed
- Applying edge caching and model compression techniques
- Monitoring and troubleshooting edge-based agents
Practical Project: Deploying a Lightweight Agent on Edge Hardware
- Designing a compact autonomous agent for IoT or robotics applications
- Implementing model inference and local logic structures
- Testing and refining for optimal latency and reliability
Conclusion and Future Directions
Requirements
- Proficiency in Python programming
- Fundamental knowledge of machine learning workflows
- Working knowledge of embedded or edge computing concepts
Target Audience
- Embedded developers integrating AI capabilities into hardware systems
- Edge ML engineers developing on-device inference solutions
- Robotics teams implementing agentic AI for autonomous operations
21 Hours
