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 14 hours
Course Outline
Introduction to Edge AI and Nano Banana
- Core attributes of edge-AI workloads
- Nano Banana architecture and functional capabilities
- Analysis of edge versus cloud deployment strategies
Preparing Models for Edge Deployment
- Selecting models and establishing baseline evaluations
- Reviewing dependencies and compatibility factors
- Exporting models for subsequent optimization
Model Compression Techniques
- Pruning strategies and the concept of structural sparsity
- Utilizing weight sharing and reducing parameter counts
- Assessing the impact of compression
Quantization for Edge Performance
- Post-training quantization methodologies
- Workflows for quantization-aware training
- Implementing INT8, FP16, and mixed-precision techniques
Acceleration with Nano Banana
- Leveraging Nano Banana accelerators
- Integrating ONNX and various hardware backends
- Benchmarking performance of accelerated inference
Deployment to Edge Devices
- Incorporating models into embedded or mobile applications
- Configuring and monitoring runtime operations
- Resolving common deployment challenges
Performance Profiling and Trade-off Analysis
- Managing latency, throughput, and thermal limits
- Navigating trade-offs between accuracy and performance
- Employing iterative optimization strategies
Best Practices for Maintaining Edge-AI Systems
- Handling version control and continuous updates
- Managing model rollbacks and system compatibility
- Addressing security and integrity requirements
Summary and Next Steps
Requirements
- A solid grasp of machine learning workflows
- Proficiency in Python-based model development
- Working knowledge of neural network architectures
Target Audience
- ML engineers
- Data scientists
- MLOps practitioners
Testimonials (1)
Flow , vibe and topic on presentation
