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 TinyML
- Defining TinyML
- The value of running machine learning on microcontrollers
- Contrasting traditional AI with TinyML
- Reviewing necessary hardware and software prerequisites
Configuring the TinyML Workspace
- Setting up the Arduino IDE and development tools
- Getting acquainted with TensorFlow Lite and Edge Impulse
- Preparing microcontrollers for TinyML tasks through flashing and configuration
Developing and Rolling Out TinyML Models
- Navigating the TinyML development lifecycle
- Training a basic machine learning model suitable for microcontrollers
- Converting AI models into the TensorFlow Lite format
- Deploying optimized models onto physical hardware
Enhancing TinyML Performance on Edge Devices
- Minimizing memory usage and computational load
- Applying quantization and model compression methods
- Measuring and benchmarking TinyML model efficiency
Practical TinyML Scenarios and Use Cases
- Implementing gesture recognition via accelerometer inputs
- Performing audio classification and keyword identification
- Utilizing anomaly detection for predictive maintenance
TinyML Obstacles and Emerging Trends
- Addressing hardware constraints and optimization tactics
- Considering security and privacy issues in TinyML deployments
- Exploring future developments and research directions in TinyML
Wrap-up and Future Pathways
Requirements
- Foundational programming skills (Python or C/C++)
- Working knowledge of machine learning concepts (suggested but not mandatory)
- Basic understanding of embedded systems (optional but beneficial)
Target Learners
- Engineers
- Data Scientists
- AI Enthusiasts
14 Hours
