Get in Touch

Course Outline

Foundations of Edge AI and an Introduction to Nano Banana

  • Distinguishing features of edge-AI workloads
  • Overview of Nano Banana’s architecture and capabilities
  • An analysis of edge versus cloud deployment strategies

Readiness for Deploying Models to the Edge

  • Choosing models and establishing baseline evaluations
  • Addressing dependencies and compatibility requirements
  • Exporting models to prepare for further optimization

Techniques for Model Compression

  • Strategies for pruning and achieving structural sparsity
  • Utilizing weight sharing and reducing parameters
  • Assessing the impact of compression on performance

Quantization Strategies for Edge Performance

  • Methods for post-training quantization
  • Workflows for quantization-aware training
  • Applications of INT8, FP16, and mixed-precision techniques

Accelerating Performance with Nano Banana

  • Leveraging Nano Banana’s accelerator capabilities
  • Integrating ONNX models with various hardware backends
  • Conducting benchmarks for accelerated inference

Implementing Models on Edge Devices

  • Embedding models within mobile or embedded applications
  • Configuring runtimes and implementing monitoring solutions
  • Resolving common deployment challenges

Profiling Performance and Analyzing Trade-offs

  • Managing latency, throughput, and thermal limitations
  • Balancing accuracy against performance metrics
  • Employing iterative strategies for optimization

Best Practices for Sustaining Edge-AI Systems

  • Managing version control and continuous updates
  • Overseeing model rollbacks and compatibility
  • Addressing security and data integrity concerns

Conclusion and Future Directions

Requirements

  • A foundational grasp of machine learning workflows
  • Practical experience in developing models using Python
  • Knowledge of neural network architectures

Target Audience

  • ML engineers
  • Data scientists
  • MLOps practitioners
 14 Hours

Testimonials (1)

Related Categories