Course Outline
Introduction to Edge AI Optimization
- General overview of edge AI and its associated challenges
- The significance of model optimization for edge devices
- Case studies featuring optimized AI models in edge applications
Model Compression Techniques
- Introduction to the concept of model compression
- Strategies for minimizing model size
- Practical exercises focused on model compression
Quantization Methods
- Overview of quantization and its advantages
- Categories of quantization (post-training, quantization-aware training)
- Practical exercises focused on model quantization
Pruning and Other Optimization Techniques
- Introduction to model pruning
- Approaches 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 evaluating optimized models
- Resolving deployment issues
- Practical exercises focused on model deployment
Tools and Frameworks for Optimization
- 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
- Practical project for building and optimizing a real-world application
Summary and Next Steps
Requirements
- A foundational grasp of AI and machine learning principles
- Practical experience in AI model development
- Fundamental programming proficiency (Python is recommended)
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.
