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 and edge computing principles
- Considerations for latency, privacy, and bandwidth
- Architectural comparison: cloud-based versus edge-based agents
Designing Lightweight Agent Architectures
- Deconstructing the agent loop for constrained systems
- Asynchronous design patterns for efficient computation
- Balancing agent autonomy with connectivity requirements
Setting Up the Development Environment
- Installing Python frameworks suited for edge AI
- Configuring TensorFlow Lite and PyTorch Mobile
- Establishing test environments on Raspberry Pi or comparable hardware
Implementing On-Device Inference
- Converting and quantising models for edge deployment
- Executing inference with TensorFlow Lite and ONNX Runtime
- Incorporating inference outcomes into agent decision-making loops
Integrating Agents with Hardware and IoT
- Linking sensors, actuators, and IoT modules
- Building local data collection and processing pipelines
- Enabling offline operation and event-triggered behaviour
Optimisation and Monitoring
- Performance tuning for low power consumption and high speed
- Edge caching strategies and model compression techniques
- Monitoring and debugging edge-based agents
Hands-on Project: Deploying a Lightweight Agent on Edge Hardware
- Designing a compact autonomous agent for IoT or robotics applications
- Implementing model inference and local logic
- Testing and refining for latency and reliability
Summary and Next Steps
Requirements
- Proficiency in Python programming
- Fundamental understanding of machine learning workflows
- Familiarity with embedded or edge computing concepts
Target Audience
- Embedded developers integrating AI capabilities into hardware systems
- Edge ML engineers designing inference solutions for on-device implementation
- Robotics teams deploying agentic AI for autonomous operations
21 Hours
