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
- Defining features of edge AI workloads
- Architecture and functionalities of Nano Banana
- Contrasting edge versus cloud deployment methods
Readying Models for Edge Deployment
- Choosing models and establishing baseline metrics
- Assessing dependencies and compatibility requirements
- Preparing models for export and optimization
Techniques for Model Compression
- Strategies for pruning and achieving structural sparsity
- Techniques for weight sharing and reducing parameters
- Assessing the impact of compression
Quantization for Enhanced Edge Performance
- Methods for post-training quantization
- Workflows for quantization-aware training
- Implementing INT8, FP16, and mixed-precision strategies
Acceleration using Nano Banana
- Leveraging Nano Banana accelerators
- Integration of ONNX and hardware backends
- Performance testing of accelerated inference
Deployment onto Edge Devices
- Embedding models into mobile or embedded applications
- Runtime setup and monitoring
- Resolving deployment challenges
Performance Analysis and Trade-off Evaluation
- Considering latency, throughput, and thermal limits
- Weighing accuracy against performance
- Strategies for iterative optimization
Best Practices for Maintaining Edge AI Systems
- Managing versioning and ongoing updates
- Handling model rollbacks and compatibility
- Addressing security and integrity requirements
Overview and Future Directions
Requirements
- Comprehension of machine learning processes
- Proficiency in Python-based model creation
- Knowledge of neural network structures
Target Participants
- ML engineers
- Data scientists
- MLOps specialists
Testimonials (1)
Flow , vibe and topic on presentation
