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
Overview of TinyML
- Definition of TinyML
- The role of machine learning in microcontroller-based systems
- Distinctions between conventional AI and TinyML approaches
- Hardware and software prerequisites
Establishing the Development Environment
- Installation of Arduino IDE and configuration of the development workspace
- Introduction to TensorFlow Lite and Edge Impulse platforms
- Flashing and configuring microcontrollers for TinyML implementation
Model Construction and Deployment
- Examination of the TinyML operational workflow
- Training a foundational machine learning model for microcontrollers
- Converting AI models to TensorFlow Lite format
- Deployment of models onto hardware devices for government and public sector applications where contextually appropriate
Optimization for Edge Devices
- Strategies for minimizing memory usage and computational requirements
- Methods for quantization and model compression
- Performance benchmarking of TinyML models
Applications and Use Cases
- Gesture recognition via accelerometer data analysis
- Audio classification and keyword spotting capabilities
- Anomaly detection for predictive maintenance protocols
Challenges and Emerging Trends
- Hardware constraints and corresponding optimization strategies
- Security and privacy considerations within TinyML frameworks
- Future developments and research directions in TinyML
Conclusion and Strategic Next Steps
Requirements
- Foundational programming proficiency in Python or C/C++
- Knowledge of machine learning principles (recommended but not mandatory)
- Understanding of embedded systems architecture (optional but advantageous)
Audience
- Engineers
- Data scientists
- AI enthusiasts
14 Hours
