Get in Touch

Course Outline

Introduction to Edge AI and Nano Banana

  • Essential characteristics of edge-AI workloads
  • Overview of Nano Banana’s architecture and capabilities
  • Comparative analysis of edge versus cloud deployment strategies

Preparing Models for Edge Deployment

  • Model selection and establishing baseline evaluations
  • Addressing dependency and compatibility considerations
  • Exporting models for subsequent optimization phases

Model Compression Techniques

  • Exploring pruning strategies and structural sparsity
  • Applying weight sharing and parameter reduction methods
  • Assessing the impact of compression on model performance

Quantization for Edge Performance

  • Implementing post-training quantization methods
  • Managing quantization-aware training workflows
  • Utilizing INT8, FP16, and mixed-precision approaches

Acceleration with Nano Banana

  • Leveraging Nano Banana accelerators
  • Integrating ONNX and hardware backends
  • Benchmarking accelerated inference processes

Deployment to Edge Devices

  • Integrating models into embedded or mobile applications
  • Configuring runtimes and monitoring systems
  • Troubleshooting common deployment challenges

Performance Profiling and Trade-off Analysis

  • Managing latency, throughput, and thermal constraints
  • Balancing accuracy against performance trade-offs
  • Applying iterative optimization strategies

Best Practices for Maintaining Edge-AI Systems

  • Implementing versioning and continuous updates
  • Managing model rollbacks and compatibility
  • Addressing security and integrity considerations

Summary and Next Steps

Requirements

  • A solid understanding of machine learning workflows
  • Experience in developing models using Python
  • Familiarity with neural network architectures

Target Audience

  • ML engineers
  • Data scientists
  • MLOps practitioners
 14 Hours

Number of participants


Price per participant

Testimonials (1)

Upcoming Courses

Related Categories