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
Foundations of TinyML and Embedded AI
- Key features of TinyML deployment
- Limits encountered in microcontroller environments
- Introduction to embedded AI toolchains
Core Principles of Model Optimization
- Recognizing computational bottlenecks
- Spotting operations that consume significant memory
- Conducting initial performance profiling
Quantization Approaches
- Strategies for post-training quantization
- Quantization-aware training methods
- Balancing accuracy against resource usage
Pruning and Compression Methods
- Techniques for structured and unstructured pruning
- Concepts of weight sharing and model sparsity
- Algorithms for compressing models for lightweight inference
Hardware-Specific Optimization
- Running models on ARM Cortex-M systems
- Optimizing for DSP and hardware accelerator features
- Considerations for memory mapping and data flow
Testing and Verification
- Analyzing latency and data throughput
- Measuring power and energy usage
- Testing for accuracy and robustness
Deployment Processes and Tooling
- Leveraging TensorFlow Lite Micro for embedded implementation
- Connecting TinyML models with Edge Impulse workflows
- Testing and troubleshooting on physical hardware
Sophisticated Optimization Tactics
- Applying neural architecture search to TinyML
- Combining quantization and pruning strategies
- Using model distillation for embedded inference
Concluding Remarks and Future Directions
Requirements
- Knowledge of machine learning workflows
- Background in embedded systems or microcontroller-based development
- Proficiency in Python programming
Target Audience
- AI researchers
- Embedded ML engineers
- Professionals involved in resource-constrained inference systems
