fbpx
Course length:
Training language:
32 lessons
English
Course fee:

349 500 HUF + VAT (cca. 905 EUR + VAT)


Course dates and application

First training day: 2 September 2024, Further training days: 3., 4., 5.

on working days (09.00 - 16.30)
Application deadline:
23 August 2024
Training language:
Hungarian
Course fee:

349 500 HUF + VAT (cca. 905 EUR + VAT)

First training day: 2 December 2024, Further training days: 3., 4., 5.

on working days (09.00 - 16.30)
Application deadline:
22 November 2024
Training language:
Hungarian
Course fee:

349 500 HUF + VAT (cca. 905 EUR + VAT)

Applying for closed-group training

If you and your colleagues are attending a closed group training course and you have a training date code, you can apply here.

Application without a date

If none of the dates is right for you, but you are interested in the course, please submit your application without a date. When we announce a new date you will be notified.

This course is designed for testers willing to take the ISTQB AI Testing exam. Students who complete the course will gain a comprehensive understanding of artificial intelligence and machine learning testing and its use in software testing.

This training is designed for software testers, software developers, test analysts and test managers who want to understand how AI can support software testing, and for those wishing to design and execute test cases in intelligent systems.

The training requires the successful completion of the ISTQB Certified Tester Foundation Level exam, and a working knowledge of English, given that both the course material and the exam are in English. Knowledge of the theoretical background of artificial intelligence is not a prerequisite for the training.

By completing the ISTQB® Certified Tester- AI Testing qualification, course participants will:

  • understand the current state of artificial intelligence and expected trends,
  • gain experience in the implementation of machine learning models,
  • become familiar with the challenges of tests completed in intelligent systems,
  • gain experience in designing and implementing test cases in intelligent systems,
  • recognise the specific requirements for testing in intelligent systems.

Our training places a strong emphasis on the theoretical background of artificial intelligence, which is also thoroughly tested in the related ISTQB exam.

 


Course Outline:

 

1. INTRODUCTION TO AI

1.1 Definition of AI and AI Effect
1.2 Narrow, General and Super AI
1.3 AI-Based and Conventional Systems
1.4 AI Technologies
1.5 AI Development Frameworks
1.6 Hardware for AI-Based Systems
1.7 AI as a Service (AIaaS)
1.7.1 Contracts for AI as a Service
1.7.2 AIaaS Examples
1.8 Pre-Trained Models
1.8.1 Introduction to Pre-Trained Models
1.8.2 Transfer Learning
1.8.3 Risks of using Pre-Trained Models and Transfer Learning
1.9 Standards, Regulations and AI
 

2. QUALITY CHARACTERISTICS FOR AI-BASED SYSTEMS

2.1 Flexibility and Adaptability
2.2 Autonomy
2.3 Evolution
2.4 Bias
2.5 Ethics
2.6 Side Effects and Reward Hacking
2.7 Transparency, Interpretability and Explainability
2.8 Safety and AI
 

 

3. MACHINE LEARNING (ML) – OVERVIEW

3.1 Forms of ML
3.1.1 Supervised Learning
3.1.2 Unsupervised Learning
3.1.3 Reinforcement Learning
3.2 ML Workflow
3.3 Selecting a Form of ML
3.4 Factors Involved in ML Algorithm Selection
3.5 Overfitting and Underfitting
3.5.1 Overfitting
3.5.2 Underfitting
3.5.3 Hands-On Exercise: Demonstrate Overfitting and Underfitting
 

4. ML - DATA

4.1 Data Preparation as Part of the ML Workflow
4.1.1 Challenges in Data Preparation
4.1.2 Hands-On Exercise: Data Preparation for ML
4.2 Training, Validation and Test Datasets in the ML Workflow
4.2.1 Hands-On Exercise: Identify Training and Test Data and Create an ML Model
4.3 Dataset Quality Issues
4.4 Data Quality and its Effect on the ML Model
4.5 Data Labelling for Supervised Learning
4.5.1 Approaches to Data Labelling
4.5.2 Mislabeled Data in Datasets

 

 

 

5. ML FUNCTIONAL PERFORMANCE METRICS

5.1 Confusion Matrix
5.2 Additional ML Functional Performance Metrics for Classification, Regression and
Clustering
5.3 Limitations of ML Functional Performance Metrics
5.4 Selecting ML Functional Performance Metrics
5.4.1 Hands-On Exercise: Evaluate the Created ML Model
5.5 Benchmark Suites for ML
 

6. ML - NEURAL NETWORKS AND TESTING

6.1 Neural Networks
6.1.1 Hands-On Exercise: Implement a Simple Perceptron
6.2 Coverage Measures for Neural Networks
 

7. TESTING AI-BASED SYSTEMS OVERVIEW

7.1 Specification of AI-Based Systems
7.2 Test Levels for AI-Based Systems
7.2.1 Input Data Testing
7.2.2 ML Model Testing
7.2.3 Component Testing
7.2.4 Component Integration Testing
7.2.5 System Testing
7.2.6 Acceptance Testing
7.3 Test Data for Testing AI-based Systems
7.4 Testing for Automation Bias in AI-Based Systems
7.5 Documenting an AI Component
7.6 Testing for Concept Drift
7.7 Selecting a Test Approach for an ML System
 

8. TESTING AI-SPECIFIC QUALITY CHARACTERISTICS

8.1 Challenges Testing Self-Learning Systems
8.2 Testing Autonomous AI-Based Systems
8.3 Testing for Algorithmic, Sample and Inappropriate Bias
8.4 Challenges Testing Probabilistic and Non-Deterministic AI-Based Systems
8.5 Challenges Testing Complex AI-Based Systems
8.6 Testing the Transparency, Interpretability and Explainability of AI-Based Systems
8.6.1 Hands-On Exercise: Model Explainability
8.7 Test Oracles for AI-Based Systems
8.8 Test Objectives and Acceptance Criteria
 
 
 

9. METHODS AND TECHNIQUES FOR THE TESTING OF AI-BASED SYSTEMS

9.1 Adversarial Attacks and Data Poisoning
9.1.1 Adversarial Attacks
9.1.2 Data Poisoning
9.2 Pairwise Testing
9.2.1 Hands-On Exercise: Pairwise Testing
9.3 Back-to-Back Testing
9.4 A/B Testing
9.5 Metamorphic Testing (MT)
9.5.1 Hands-On Exercise: Metamorphic Testing
9.6 Experience-Based Testing of AI-Based Systems
9.6.1 Hands-On Exercise: Exploratory Testing and Exploratory Data Analysis (EDA)
9.7 Selecting Test Techniques for AI-Based Systems

 

10. TEST ENVIRONMENTS FOR AI-BASED SYSTEMS

10.1 Test Environments for AI-Based Systems
10.2 Virtual Test Environments for Testing AI-Based Systems
 

11. USING AI FOR TESTING

11.1 AI Technologies for Testing
11.1.1 Hands-On Exercise:The Use of AI in Testing
11.2 Using AI to Analyze Reported Defects
11.3 Using AI for Test Case Generation
11.4 Using AI for the Optimization of Regression Test Suites
11.5 Using AI for Defect Prediction
11.5.1 Hands-On Exercise: Build a Defect Prediction System
11.6 Using AI for Testing User Interfaces
11.6.1 Using AI to Test Through the Graphical User Interface (GUI)
11.6.2 Using AI to Test the GUI

 

Do you have any questions about the training?



FOUNDATION TRAININGS FOR THIS COURSE

Don't have enough knowledge to complete this training yet? Then get the basics you need with these courses.


ISTQB Certified Tester Foundation Level live course
(MFECTFL)

Length:
24 lessons
Price:

219 500 HUF + VAT (cca. 595 EUR + VAT)

Training dates:
Jun 17
Aug 21
Oct 14
ISTQB Certified Tester Foundation Level e-learning
(MFCTFLE)

Price:
89 500 HUF + VAT
This hands-on course provides test engineers and test managers with the essential ideas, processes, tools and skills they need in order to set themselves on a path for true testing professionalism. This course was accredited by the ASTQB August 2018. This course follows the ISTQB Foundation Level Syllabus 2018.

You may also be interested in these courses and e-learning packages

You may find the courses below interesting


ISTQB Foundation Level - Agile Tester Extension course
(MFCTAGILE)

Length:
16 lessons
Price:
129 500 HUF + VAT
Training dates:
Aug 01
ISTQB Foundation Level - Agile Tester Extension e-learning
(MFCTAGILEE)

Price:
69 500 HUF + VAT
This course provides testers and test managers with an understanding of the fundamentals of testing on agile projects. Attendees will learn how agile software development projects are organized and the various types of agile development practices in common use. They will understand how agile development differs from traditional approaches, how to position testers in an agile organisation, the fundamental agile testing principles, practices and processes and the skills they’ll need to excel in an agile environment.
ISTQB Certified Tester Advanced Level Test Manager e-learning
(MFCTALTME)

Price:
109 500 HUF + VAT
This course provides test managers with advanced skills in test estimation, test planning, test monitoring and test control. Attendees will learn how to define the overall testing goals and strategy for the systems being tested. They will gain hands-on experience in planning, scheduling and tracking these tasks. The attendees will be able to describe and organize the necessary activities. They will return to work able to select, acquire and assign adequate resources for testing tasks. They will know how to form, organize and lead testing teams. Test manager attendees will be able to organize communication between the members of the testing teams and between the testing teams and all the other stakeholders. Further, they’ll learn how to justify their decisions and provide adequate reporting information where applicable.
ISTQB Certified Tester Advanced Level Test Analyst e-learning
(MFCTALTAE)

Price:
109 500 HUF + VAT
This course provides Test Analysts with advanced skills in test analysis, design, and execution.  This hands-on course provides Test Analysts with the ability to define and carry out the tasks required to put the test strategy into action.  The course will teach attendees how to analyze the system, taking into account the organization’s and user’s quality expectations.  They will learn how to evaluate system requirements as part of formal and informal reviews, leveraging their understanding of the business domain to determine requirement validity.  Attendees will learn how to analyze, design, implement, and execute tests, using risk considerations to determine the appropriate effort and priority for tests. Attendees will learn how to implement a testing effort that supports the explicit and implicit testing objectives.
ISTQB Advanced Level Technical Test Analyst e-learning
(MFCTALTTAE)

Price:
109 500 HUF + VAT
This training course presents a comprehensive overview of methods and techniques for deriving and specifying software tests based on the system’s implementation and structure (“white box tests”). On completing the course, attendees will be able to select and apply techniques for test case derivation, such as control flow or data flow testing as well as static and dynamic analysis. We will look at non-functional testing techniques, such as reliability testing, portability testing, performance, load and stress testing. We will also discuss how to succeed in building robust automation architectures and using a variety of tools to reach quality targets.