Course description
This comprehensive program is designed for professionals involved in testing systems based on artificial intelligence or planning to use AI tools for testing purposes.
Our accredited training materials, based on the official syllabus of the International Software Testing Qualifications Board, provide comprehensive preparation for the CT-AI certification exam.
The professional development program offers both theoretical and practical knowledge, enabling participants to effectively test, optimize, and ensure the quality of AI-based systems and processes.
Our training places strong emphasis on the theoretical foundations of artificial intelligence, which are also thoroughly assessed in the associated ISTQB exam.
Key topics:
Introduction to AI
You will learn the basic concepts of artificial intelligence, its types (narrow, general, and super AI), technologies, development frameworks, and AI-as-a-service solutions.
Quality characteristics of AI systems
You will explore key quality factors of AI systems, including flexibility, ethics, bias, transparency, and security.
Overview of machine learning
You will gain an understanding of machine learning types, workflows, algorithm selection, and issues such as overfitting and underfitting.
Data preparation and management for ML
You will master data preparation steps, the importance of dataset quality, and the role of annotation in machine learning models.
ML performance metrics
You will learn to apply and evaluate model performance metrics for classification, regression, and clustering.
Neural networks and their testing
You will dive into the functioning and testing of neural networks, including coverage metrics and implementation of simple perceptrons.
Overview of AI system testing
You will understand levels of AI system testing, including data testing, integration testing of components and systems, and acceptance testing.
Testing AI-specific quality characteristics
You will explore how to test AI systems in terms of autonomy, learning capability, bias, and transparency.
Methods and techniques for testing AI systems
You will master AI-specific testing techniques such as adversarial attacks, data poisoning, and metamorphic testing.
AI testing environments
You will learn the importance of virtual test environments in validating AI systems and testing operational models.
Use of AI in testing
You will discover how AI tools can be used for test case generation, defect prediction, regression test optimization, and UI testing.
After completing the International Software Testing Qualifications Board Certified Tester – AI Testing qualification, participants will:
- understand the current state of artificial intelligence and expected trends,
- gain experience implementing machine learning models,
- become familiar with challenges in testing intelligent systems,
- gain experience in designing and implementing test cases for intelligent systems,
- recognize specific requirements for testing intelligent systems.
