A company is using ML to predict the presence of a specific weed in a farmer's field. The company is using the Amazon SageMaker linear learner built-in algorithm with a value of multiclass_dassifier f

Question

Options

• ASet the value of the weight decay hyperparameter to zero.
• BIncrease the number of training epochs.
• CIncrease the value of the target_precision hyperparameter.
• DChange the value of the predictorjype hyperparameter to regressor.

• A
  9% (4)
• B
  5% (2)
• C
  81% (35)
• D
  5% (2)

Explanation

Increasing target_precision directly controls the precision-recall tradeoff in SageMaker's linear learner: a higher target precision forces the model to only predict "weed present" when highly confident, which directly minimizes false positives (predicting weed when none exists). Option A is wrong because weight decay is a regularization technique that combats overfitting but has no direct effect on the precision-recall balance. Option B is wrong because more training epochs may improve overall accuracy but don't specifically shift the decision threshold toward higher precision. Option D is wrong because switching to a regressor outputs continuous values rather than class labels, making it incompatible with a classification task and irrelevant to controlling false positives.

Memory tip: Think "precision = being precise (picky) before saying yes" - raising target_precision makes the model pickier about predicting the positive class, so it flags fewer false alarms.

No community discussion yet for this question.