DP-100 Question #436: Real Exam Question with Answer & Explanation

Question

You have an Azure Machine Learning workspace. You plan to tune a model hyperparameter when you train the model. You need to define a search space that returns a normally distributed value. Which parameter should you use?

Options

• AQUniform
• BLogUniform
• CUniform
• DLogNormal

Explanation

{"question_number": 1, "question": "You have an Azure Machine Learning workspace. You plan to tune a model hyperparameter when you train the model. You need to define a search space that returns a normally distributed value. Which parameter should you use?", "correct_answer": "D. LogNormal", "explanation": "In Azure ML hyperparameter tuning, the search space sampling functions map to statistical distributions. 'LogNormal(mu, sigma)' returns a value whose logarithm follows a normal distribution - making it the distribution in the list rooted in the normal (Gaussian) curve. 'Uniform' samples evenly between two bounds. 'LogUniform' samples uniformly in log-space (the exponent of a uniform draw), producing no normal-distribution properties. 'QUniform' is a quantized (rounded) variant of Uniform. Because LogNormal is the only choice whose underlying math involves a normal distribution, it is the correct answer.", "generated_by": "claude-sonnet", "llm_judge_score": 3}

No community discussion yet for this question.