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.
Duration 21 hours
Course Outline
Introduction to TinyML and Embedded AI
- Key characteristics of TinyML model deployment
- Specific constraints within microcontroller environments
- Overview of essential embedded AI toolchains
Foundations of Model Optimization
- Identifying and understanding computational bottlenecks
- Recognizing memory-intensive operations
- Establishing baseline performance profiles
Quantization Methodologies
- Strategies for post-training quantization
- Implementing quantization-aware training
- Balancing accuracy against resource utilization
Pruning and Compression Strategies
- Application of structured and unstructured pruning
- Leveraging weight sharing and model sparsity
- Utilizing compression algorithms for lightweight inference
Hardware-Aware Optimization
- Model deployment on ARM Cortex-M systems
- Optimizing for DSP and accelerator extensions
- Considering memory mapping and dataflow architectures
Benchmarking and Validation
- Analyzing latency and throughput
- Measuring power and energy consumption
- Testing for accuracy and robustness
Deployment Workflows and Tooling
- Utilizing TensorFlow Lite Micro for embedded deployment
- Integrating TinyML models with Edge Impulse pipelines
- Performing testing and debugging on physical hardware
Advanced Optimization Strategies
- Applying Neural Architecture Search for TinyML
- Combining quantization and pruning in hybrid approaches
- Using model distillation for embedded inference
Conclusion and Future Directions
Requirements
- A solid grasp of machine learning workflows
- Practical experience in embedded systems or microcontroller-based development
- Proficiency in Python programming
Target Audience
- AI Researchers
- Embedded ML Engineers
- Professionals specializing in resource-constrained inference systems
