Course Outline
Introduction to Edge AI Optimization
- An overview of edge AI and its associated challenges
- The critical role of model optimization for edge devices
- Case studies highlighting optimized AI models in edge applications
Model Compression Techniques
- An introduction to model compression
- Strategies for minimizing model size
- Practical exercises focused on model compression
Quantization Methods
- An overview of quantization and its advantages
- Different types of quantization (post-training and quantization-aware training)
- Practical exercises focused on model quantization
Pruning and Other Optimization Techniques
- An introduction to pruning
- Methods for pruning AI models
- Additional optimization techniques (e.g., knowledge distillation)
- Practical exercises focused on model pruning and optimization
Deploying Optimized Models on Edge Devices
- Setting up the edge device environment
- Deploying and testing optimized models
- Resolving common deployment issues
- Practical exercises focused on model deployment
Tools and Frameworks for Optimization
- An overview of relevant tools and frameworks (e.g., TensorFlow Lite, ONNX)
- Utilizing TensorFlow Lite for model optimization
- Practical exercises using optimization tools
Real-World Applications and Case Studies
- Review of successful edge AI optimization projects
- Discussion of industry-specific use cases
- A hands-on project involving the creation and optimization of a real-world application
Summary and Next Steps
Requirements
- A solid grasp of AI and machine learning fundamentals
- Prior experience in developing AI models
- Foundational programming skills (Python is preferred)
Target Audience
- AI developers
- Machine learning engineers
- System architects
Testimonials (2)
the ML ecosystem not only MLFlow but Optuna, hyperops, docker , docker-compose
Guillaume GAUTIER - OLEA MEDICAL
Course - MLflow
I enjoyed participating in the Kubeflow training, which was held remotely. This training allowed me to consolidate my knowledge for AWS services, K8s, all the devOps tools around Kubeflow which are the necessary bases to properly tackle the subject. I wanted to thank Malawski Marcin for his patience and professionalism for training and advice on best practices. Malawski approaches the subject from different angles, different deployment tools Ansible, EKS kubectl, Terraform. Now I am definitely convinced that I am going into the right field of application.
