Course Outline
Instructional Syllabus Training Proposal for Government
Day 1 - Foundations of AI and Python in Data Processing
• Current status of the artificial intelligence and machine learning ecosystem
• Application of AI within contemporary data engineering practices
• Review of essential Python programming techniques for AI deployment
• Utilizing pandas and NumPy libraries for data manipulation
• Fundamentals of API interaction and JSON data processing
• Practical activity: Ingesting and processing structured datasets
Day 2 - Core Machine Learning Principles for Operational Use
• Theoretical foundations of supervised and unsupervised learning models
• Strategies for feature engineering and data preprocessing
• Foundational model training processes utilizing scikit-learn
• Assessment frameworks and key performance indicators
• Overview of model deployment methodologies
• Practical exercise: Developing a basic predictive analytics model
Day 3 - Fundamentals of Large Language Models and Prompt Structuring
• Operational mechanisms of large language models and their architecture
• Concepts of tokenization, context limits, and system constraints
• Best practices and methodologies for prompt architecture
• Application of zero-shot and few-shot prompting techniques
• Evaluation protocols and iterative refinement strategies
• Practical exercises: Engineering effective prompts for specific tasks
Day 4- Development of AI Applications Utilizing LLMs
• Integration of LLM APIs within Python environments
• Standards for structured data output and function calling protocols
• Development of interactive chat interfaces and task-oriented systems
• Overview of retrieval-augmented generation techniques
• Linking LLM capabilities with external data repositories
• Capstone activity: Constructing a basic AI-powered assistant
Day 5 - Deployment of AI Solutions in Production Environments
• Architectural design for scalable AI processing workflows
• Incorporation of AI components into existing data pipelines
• Continuous monitoring and performance enhancement protocols
• Budgetary efficiency and API consumption management strategies
• Security frameworks and ethical guidelines for responsible AI
• Capstone project: Implementation of a comprehensive AI solution
Testimonials (2)
The trainer was very available to answer all te kind of question I did
Caterina - Stamtech
Course - Developing APIs with Python and FastAPI
Trainer develops training based on participant's pace