AI Workshop for Developers: Basics of Open Source Solutions in Practice

Course content aims to provide participants with a fundamental understanding of Artificial Intelligence (AI) and Machine Learning. The course covers a wide range of thematic areas, from the history and definitions of AI to practical demonstrations in Python using the interactive Jupyter platform. Participants will become acquainted with machine learning algorithms, data manipulation in Python, and applications such as TXTAI and Huggingface for semantic search and language processing. The course's key focus is on Open Source solutions.

Target Audience:

• IT Specialists
• Software and Data Engineers
• Data Analysts

Course Objectives:

• Provide IT specialists with a basic understanding of key AI principles, including machine learning, neural networks, and practical applications in Python using the interactive Jupyter platform.

Course Outline:

1. Introduction to AI and Machine Learning

   • History and definitions of AI
   • Overview of different AI areas
   • Classification of machine learning: supervised, unsupervised, reinforcement learning

2. Basics of Machine Learning

   • Machine learning algorithms: linear regression, logistic regression, decision trees
   • Model training, validation, and testing
   • Interactive demonstrations in Jupyter

3. Working with Datasets

   • Basics of data manipulation in Python (pandas, numpy)
   • Data preparation and cleaning
   • Practical exercises with real datasets

4. TXTAI and Huggingface - Basics of Open Source Solutions

   • Practical Jupyter examples
   • Semantic search
   • Categorization
   • Text summarization
   • Extraction of text from various document types
   • Text translations
   • Similar image search
   • Custom document indexing
   • Training custom models
   • Creating a simple "prompt-driven" search
   • Specifics of the Czech language in NLP

5. Working with NLP Models

   • Creating processing pipelines
   • Considerations and precautions
   • Ethics, Future of AI, Discussion

6. Discussion of ethical issues and the future direction of AI

   • Interactive Q&A and course conclusion

Teaching Methods:

• Interactive presentations
• Hands-on exercises in Jupyter Notebooks
• Group discussions and Q&A sessions

Technical Requirements:

• Internet access
• Pre-installed Jupyter Notebook (or use of online services like Binder or Google Colab)
• Sample Jupyter Notebooks (provided before the course)

Participant Prerequisites:

• Basic programming knowledge (Python preferred)
• Basic knowledge of statistics