A tech firm wants to assess a candidate’s grasp of ML and DL fundamentals for a new recommendation engine project.

Explain the difference between overfitting and underfitting and how to detect each. Name two advantages of deep learning over traditional machine-learning models and two disadvantages. Why are activation functions like ReLU preferred over sigmoid in deep networks? How do convolutional layers differ from fully connected layers in terms of parameter sharing and receptive field?

Focus on general concepts—no math derivations required.

Boston-consulting-group Data Scientist interview question: Differentiate Overfitting and Underfitting in Machine Learning. {"blocks": [{"key": "a575e336", "text": "Scenario", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {...