Course Outline
Foundations of Edge AI Optimization
- Insights into edge AI and the inherent challenges it presents
- The critical role of model optimization in edge device contexts
- Analysis of case studies featuring optimized AI models in edge applications
Strategies for Model Compression
- Core concepts of model compression
- Techniques for minimizing model footprint
- Practical exercises focused on model compression
Quantization Approaches
- Understanding quantization and its advantages
- Exploring quantization types, including post-training and quantization-aware training
- Hands-on tasks for implementing model quantization
Pruning and Advanced Optimization Techniques
- Introduction to the pruning process
- Various methodologies for pruning AI models
- Additional optimization methods, such as knowledge distillation
- Practical exercises in model pruning and optimization
Deploying Refined Models to Edge Hardware
- Setting up the edge device environment
- Processes for deploying and validating optimized models
- Strategies for resolving deployment-related issues
- Practical exercises in model deployment
Optimization Tools and Frameworks
- Survey of key tools and frameworks, such as TensorFlow Lite and ONNX
- Leveraging TensorFlow Lite for model optimization
- Hands-on practice with various optimization tools
Practical Applications and Case Studies
- Examination of successful edge AI optimization initiatives
- Discussion of industry-specific use cases
- Capstone project involving the construction and optimization of a real-world application
Wrap-Up and Future Directions
Requirements
- A solid grasp of fundamental AI and machine learning principles.
- Proven experience in developing AI models.
- Foundational programming proficiency (Python is highly recommended).
Intended Audience
- AI developers.
- Machine learning engineers.
- System architects.
Testimonials (3)
I really liked the end where we took the time to play around with CHAT GPT. The room was not set up the best for this- instead of one large table a couple of small ones so we could get into small groups and brainstorm would have helped
Nola - Laramie County Community College
Course - Artificial Intelligence (AI) Overview
Working from first principles in a focused way, and moving to applying case studies within the same day
Maggie Webb - Department of Jobs, Regions, and Precincts
Course - Artificial Neural Networks, Machine Learning, Deep Thinking
That it was applying real company data. Trainer had a very good approach by making trainees participate and compete