Course Outline
Introduction to Edge AI Optimisation
- Overview of edge AI and its associated challenges
- The importance of model optimisation for edge devices
- Case studies showcasing optimised AI models in edge applications
Model Compression Techniques
- Introduction to model compression
- Techniques for reducing model size
- Hands-on exercises for model compression
Quantisation Methods
- Overview of quantisation and its benefits
- Types of quantisation (post-training, quantisation-aware training)
- Hands-on exercises for model quantisation
Pruning and Other Optimisation Techniques
- Introduction to pruning
- Methods for pruning AI models
- Other optimisation techniques (e.g., knowledge distillation)
- Hands-on exercises for model pruning and optimisation
Deploying Optimised Models on Edge Devices
- Preparing the edge device environment
- Deploying and testing optimised models
- Troubleshooting deployment issues
- Hands-on exercises for model deployment
Tools and Frameworks for Optimisation
- Overview of tools and frameworks (e.g., TensorFlow Lite, ONNX)
- Using TensorFlow Lite for model optimisation
- Hands-on exercises with optimisation tools
Real-World Applications and Case Studies
- Review of successful edge AI optimisation projects
- Discussion of industry-specific use cases
- Hands-on project for building and optimising a real-world application
Summary and Next Steps
Requirements
- A solid understanding of AI and machine learning concepts
- Experience in AI model development
- Basic programming skills (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.
