Your question is What is Dropout. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
What is dropout?
Asked in the Onsite stage. Asked during the ML fundamentals / trivia portion of the interview.
Explain the mechanism mathematically and intuitively. Describe how dropout differs between training and inference, why scaling is required, what problem it addresses, and when it may be inappropriate. Include practical considerations for selecting the dropout rate and diagnosing underfitting or overfitting.
