TinyML Fundamentals is a practical two-day training program designed to introduce participants to deploying machine learning models on ultra-low-power, resource-constrained devices such as microcontrollers. This course focuses on the core concepts of TinyML, edge intelligence, model optimization, and real-world use cases, enabling learners to understand how intelligent applications can run directly on embedded hardware without relying on cloud connectivity.

• Understand TinyML fundamentals
• Learn AI on edge devices concepts
• Understand lightweight ML model workflows
• Gain knowledge of embedded AI basics
• Learn low-power AI processing techniques
• Understand TinyML deployment concepts
• Explore IoT and sensor integration
• Identify TinyML use cases

• Embedded systems and IoT engineers
• AI and machine learning practitioners exploring edge AI
• Electronics and hardware engineers
• Product developers working on smart devices
• Technology professionals interested in low-power AI solutions

• Basic understanding of machine learning or artificial intelligence concepts
• Familiarity with embedded systems or IoT concepts is beneficial
• Awareness of sensors and data collection processes
• No advanced programming or hardware design background required

• Understanding core TinyML concepts and workflows
• Differentiating cloud AI, edge AI, and TinyML
• Identifying use cases suitable for TinyML deployment
• Interpreting constraints of memory, power, and latency
• Applying responsible and practical TinyML design principles

By the end of this training, participants will be able to explain how TinyML enables machine learning on microcontrollers, identify suitable use cases, understand model optimization strategies, evaluate deployment constraints, and contribute effectively to the design and adoption of low-power intelligent edge solutions.

Introduction to TinyML and Edge Intelligence
• What TinyML is and why it matters
• Difference between cloud AI, edge AI, and TinyML
• Hardware constraints and opportunities
• Typical TinyML application scenarios

TinyML Architecture and Workflow
• Data collection from sensors
• Training vs deployment lifecycle
• Model conversion and optimization overview
• Running inference on microcontrollers

TinyML Use Cases and Examples
• Keyword spotting and audio recognition
• Gesture and motion detection
• Anomaly detection on sensor data
• Smart devices and industrial applications

Model Optimization for TinyML
• Model size and memory constraints
• Quantization and compression concepts
• Balancing accuracy, latency, and power
• Evaluating TinyML model performance

Deployment Considerations and Challenges
• Integrating models with embedded firmware
• Latency and real-time constraints
• Debugging and monitoring TinyML systems
• Reliability and robustness in the field

Ethics, Security, and Responsible TinyML
• Data privacy on edge devices
• Security risks and model protection
• Responsible AI on constrained devices
• Sustainable and energy-efficient AI design

• TinyML fundamentals
• Edge AI concepts
• Embedded ML workflows
• Lightweight model optimization
• Sensor and IoT integration
• Low-power AI processing
• TinyML deployment techniques
• Real-time inference basics
• Performance optimization concepts
• Practical TinyML scenarios

• TinyML use case identification exercise
• Model optimization and constraint analysis activity
• Deployment scenario discussion
• Final knowledge evaluation quiz

Participants will receive course materials, slides, reference materials, exercises and access to resources for further learning.

Participants who successfully complete the training will receive an AcadNXT Certification in TinyML Fundamentals Training, validating their expertise in understanding TinyML concepts, edge AI workflows, deployment constraints, and responsible low-power AI practices.