ABOUT THE COURSE

With the current trends in technology and the growing incorporation of Artificial Intelligence and Machine Learning, Artificial Intelligence United (AiU) was created to support the understanding of implementation of these important advancements. AiU - Certified Tester in Artificial Intelligence (AiU-CTAI) is a 3-day practical certification course, which goes beyond the fundamentals of Artificial Intelligence and Machine Learning, to discover the differences associated with testing in this new world. Join the Artificial Intelligence United community and embark on your AI/ML journey today.

Target Audience

Anybody who has to test or manage testing of systems that involve AI.

Pre-requisites

In general, there are no prerequisites for attending an AiU course or taking the exam. We do recommend you hold the ISTQB CTFL certificate and have first hand experience in the field of AI & ML.

Course Duration

3 days

Course Outline:

1. Fundamentals of AI, Machine Learning and Life Cycle

  • Introduction to AI
    • Types of AI
    • AI Use cases
    • Skills for AI professional
    • AI, ML and DL
    • Types of AI Applications
  • Machine Learning and AI
    • Types of Machine Learning
    • Reinforcement Learning
    • Deep Learning
  • Life Cycle of Machine Learning
    • Process
    • Types of ML Scenarios
    • Identification Framework for ML
    • Data Preparation and Preprocessing for ML

2. Testing needs and Metrics for AI/ML/DL systems

  • Basic Testing needs for Machine Learning/AI systems
    • What does AI testing mean
    • Difference between AI testing and traditional testing
    • Challenges to test AI-based SW
  • Role of Metrics
    • Parameters to evaluate for a learning system and Model Evaluation
    • Metrics for Unsupervised Clustering
    • Metrics for Unsupervised Association Rule Mining
    • Metrics for Supervised Classification
    • Metrics for Supervised Regression
    • Underfitting , Overfitting, and Bias Variance Tradeoff
    • Metrics for Deep Learning based Classification
    • Metrics for Deep learning based Regression

3. Practical Testing of AI systems

  • Test Life Cycle for machine learning
    • Strategies to test AI applications
    • Greenfield Testing the model
    • Brownfield Testing the non-AI part
    • Testing the AI-NonAI interaction
    • Testing non-functional aspects
    • White-box v/s black-box testing for AI software
    • Other considerations
  • Interpreting ML/DL models
    • LIME Tool (Local Interpretable Model Agnostic Explanations)
    • GRAD-CAM based explanation
    • Example based explanation
    • Shapely values
    • Generation of test ideas - Linguistic analysis
  • Case studies
    • Testing chat-bots
    • Testing image classifiers
    • Testing NLP
    • Testing sentiment analysis apps
    • Testing fraud detection apps

4. AI in Testing

  • AI based test case identification
  • AI based test case automation and execution
  • Automated Defect prediction using ML
  • AI based impact analysis and defect assignment
  • User experience oriented testing
  • AI Driven Testing Tools Ecosystem
  • AI to test AI
  • Some examples of using AI for testing apps (non-AI)

5. Future of AI in testing

  • Automation of AI testing
  • Newer Explainability testing models

Mode: Hands On, Written Exercises, Group Discussion, Case Study etc

For queries contact: Vinay at +91 9910105147 / vinay@veritysoftware.in