Which term describes AI systems that combine rule-based and ML algorithms to achieve accuracy and reliability?

• A. Hybrid approaches
• B. Data privacy issues
• C. Explainable AI (XAI)
• D. Deep learning

Answer: (A)

Hybrid approaches combine symbolic, rule-based reasoning with data-driven machine learning. This mix lets systems encode explicit domain knowledge, constraints, and transparent rules while also learning from data to detect patterns, adapt to new situations, and handle uncertainty. By leveraging both strengths, accuracy and reliability can improve because the rules provide structure and safety, and the ML component handles nuance and changes in the data. For example, in a medical decision support system, rules can enforce evidence-based guidelines and safety constraints, while ML analyzes patient data to identify subtle risk signals that rules alone might miss. The other options don’t describe this integration: data privacy issues focus on protecting information, not how AI methods are combined; Explainable AI is about making decisions understandable, which may be a goal of some hybrid systems but doesn’t name the method of combining rule-based and ML components; deep learning is a specific ML approach without an inherent rule-based component.