Get in Touch

Course Outline

Overview of Edge AI and Nano Banana

  • Defining traits of edge-AI tasks
  • Nano Banana design and functional capabilities
  • Contrasting edge and cloud deployment approaches

Getting Models Ready for Edge Deployment

  • Selecting models and establishing performance baselines
  • Considering dependencies and compatibility issues
  • Exporting models for subsequent optimization

Techniques for Model Compression

  • Strategies for pruning and achieving structural sparsity
  • Sharing weights and reducing parameters
  • Assessing the effects of compression

Using Quantization for Edge Efficiency

  • Methods for post-training quantization
  • Workflows involving quantization-aware training
  • Techniques involving INT8, FP16, and mixed precision

Speeding Up Inference with Nano Banana

  • Utilizing Nano Banana accelerators
  • Integrating ONNX with hardware backends
  • Testing the performance of accelerated inference

Deploying to Edge Devices

  • Incorporating models into embedded or mobile applications
  • Configuring and monitoring the runtime environment
  • Resolving deployment-related problems

Performance Analysis and Trade-off Evaluation

  • Factors including latency, throughput, and thermal limits
  • Balancing accuracy against performance
  • Strategies for iterative optimization

Best Practices for Sustaining Edge-AI Systems

  • Managing versioning and continuous updates
  • Handling model rollbacks and compatibility
  • Considerations for security and data integrity

Concluding Summary and Future Steps

Requirements

  • Knowledge of machine learning processes
  • Background in developing models using Python
  • Understanding of neural network structures

Target Audience

  • ML engineers
  • Data scientists
  • MLOps practitioners
 14 Hours

Number of participants


Price per participant

Testimonials (1)

Upcoming Courses

Related Categories