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
Getting Started with TinyML
- Definition and scope of TinyML
- The value of running machine learning on microcontrollers
- Contrasting conventional AI with TinyML
- Summary of necessary hardware and software prerequisites
Preparing the TinyML Setup
- Installing the Arduino IDE and configuring the development space
- Overview of TensorFlow Lite and Edge Impulse
- Flashing and configuring microcontrollers for TinyML tasks
Creating and Implementing TinyML Models
- Grasping the TinyML workflow
- Training a basic machine learning model for microcontrollers
- Transforming AI models into TensorFlow Lite format
- Deploying models onto physical hardware
Refining TinyML for Edge Devices
- Minimizing memory and computational impact
- Methods for quantization and model compression
- Evaluating the performance of TinyML models
TinyML in Practice and Case Studies
- Detecting gestures via accelerometer data
- Classifying audio and identifying keywords
- Detecting anomalies for predictive maintenance
TinyML Obstacles and Emerging Trends
- Hardware constraints and optimization tactics
- Security and privacy considerations in TinyML
- Future developments and research in TinyML
Recap and Further Steps
Requirements
- Fundamental coding skills (in Python or C/C++)
- Awareness of machine learning principles (suggested but not mandatory)
- Knowledge of embedded systems (optional yet beneficial)
Target Audience
- Engineers
- Data scientists
- Enthusiasts of AI technologies
14 Hours
