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
Foundations of Edge AI and Nano Banana
- Essential attributes of edge-AI tasks
- Nano Banana design and features
- Contrasting edge and cloud deployment approaches
Readying Models for Edge Integration
- Selecting models and establishing performance baselines
- Addressing dependencies and compatibility factors
- Exporting models for advanced optimization
Strategies for Model Compression
- Pruning techniques and structural sparsity
- Parameter reduction via weight sharing
- Assessing the impact of compression
Quantization Strategies for Edge Efficiency
- Post-training quantization procedures
- Workflows for quantization-aware training
- Application of INT8, FP16, and mixed-precision methods
Speeding Up Inference with Nano Banana
- Leveraging Nano Banana acceleration features
- Integration of ONNX and hardware backends
- Benchmarking accelerated inference performance
Deploying to Edge Hardware
- Incorporating models into embedded or mobile applications
- Configuring and monitoring runtime environments
- Resolving deployment-related challenges
Performance Analysis and Trade-off Evaluation
- Managing latency, throughput, and thermal limits
- Balancing accuracy against performance
- Employing iterative optimization techniques
Best Practices for Sustaining Edge-AI Systems
- Managing versions and continuous updates
- Handling model rollbacks and compatibility
- Addressing security and integrity requirements
Overview and Future Directions
Requirements
- A solid grasp of machine learning processes
- Proficiency in developing models using Python
- Knowledge of neural network structures
Target Participants
- Machine Learning Engineers
- Data Scientists
- MLOps Specialists
Testimonials (1)
Flow , vibe and topic on presentation
