Get in Touch

Course Outline

Introduction to Edge AI and Nano Banana

  • Defining the key characteristics of edge AI workloads.
  • Overview of Nano Banana’s architecture and core capabilities.
  • Contrasting edge and cloud deployment strategies.

Preparing Models for Edge Deployment

  • Model selection and establishing baseline evaluations.
  • Assessing dependencies and compatibility requirements.
  • Exporting models ready for further optimization.

Model Compression Techniques

  • Pruning methods and structural sparsity.
  • Weight sharing and parameter minimization.
  • Measuring the impact of compression on model performance.

Quantization for Edge Performance

  • Post-training quantization techniques.
  • Workflows for quantization-aware training.
  • Approaches involving INT8, FP16, and mixed precision.

Acceleration with Nano Banana

  • Leveraging Nano Banana accelerators.
  • Integrating ONNX and hardware-specific backends.
  • Conducting benchmarks on accelerated inference.

Deployment to Edge Devices

  • Embedding models into mobile or embedded applications.
  • Managing runtime configuration and monitoring.
  • Resolving common deployment challenges.

Performance Profiling and Trade-off Analysis

  • Managing latency, throughput, and thermal limits.
  • Balancing accuracy against performance metrics.
  • Employing iterative optimization tactics.

Best Practices for Maintaining Edge-AI Systems

  • Managing versioning and continuous updates.
  • Handling model rollbacks and compatibility issues.
  • Addressing security and data integrity concerns.

Summary and Next Steps

Requirements

  • Working knowledge of machine learning workflows.
  • Practical experience with Python-based model development.
  • Proficiency 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