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 scenarios
- Limitations within microcontroller ecosystems
- Survey of embedded AI development toolchains
Core Principles of Model Optimization
- Recognizing computational bottlenecks
- Detecting operations with high memory demands
- Establishing baseline performance profiles
Strategies for Quantization
- Post-training quantization approaches
- Quantization-aware training methodologies
- Balancing accuracy against resource consumption
Methods for Pruning and Compression
- Techniques for structured and unstructured pruning
- Utilizing weight sharing and model sparsity
- Compression algorithms tailored for lightweight inference
Hardware-Centric Optimization
- Deploying models on ARM Cortex-M architectures
- Enhancing performance via DSP and accelerator extensions
- Considerations for memory mapping and dataflow
Performance Benchmarking and Verification
- Analyzing latency and throughput metrics
- Measuring power draw and energy usage
- Testing for accuracy and system robustness
Deployment Processes and Tooling
- Leveraging TensorFlow Lite Micro for embedded integration
- Connecting TinyML models with Edge Impulse workflows
- Debugging and testing on physical hardware
Sophisticated Optimization Tactics
- Applying neural architecture search to TinyML
- Combining quantization and pruning in hybrid strategies
- Using model distillation for embedded inference
Conclusion and Future Directions
Requirements
- A solid grasp of machine learning processes
- Practical experience with embedded systems or microcontroller development
- Proficiency in Python programming
Target Audience
- AI Researchers
- Embedded ML Engineers
- Professionals specializing in resource-constrained inference systems
