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
Introduction to TinyML and Embedded AI
- Key characteristics of TinyML model deployment.
- Constraints in microcontroller environments.
- Overview of embedded AI toolchains.
Model Optimization Foundations
- Understanding computational bottlenecks.
- Identifying memory-intensive operations.
- Baseline performance profiling.
Quantization Techniques
- Post-training quantization strategies.
- Quantization-aware training.
- Evaluating accuracy versus resource trade-offs.
Pruning and Compression
- Structured and unstructured pruning methods.
- Weight sharing and model sparsity.
- Compression algorithms for lightweight inference.
Hardware-Aware Optimization
- Deploying models on ARM Cortex-M systems.
- Optimizing for DSP and accelerator extensions.
- Memory mapping and dataflow considerations.
Benchmarking and Validation
- Latency and throughput analysis.
- Power and energy consumption measurements.
- Accuracy and robustness testing.
Deployment Workflows and Tools
- Using TensorFlow Lite Micro for embedded deployment.
- Integrating TinyML models with Edge Impulse pipelines.
- Testing and debugging on real hardware.
Advanced Optimization Strategies
- Neural architecture search for TinyML.
- Hybrid quantization-pruning approaches.
- Model distillation for embedded inference.
Summary and Next Steps
Requirements
- A solid understanding of machine learning workflows.
- Experience with embedded systems or microcontroller-based development.
- Familiarity with Python programming.
Target Audience
- AI researchers.
- Embedded ML engineers.
- Professionals working on resource-constrained inference systems.
21 Hours
