Technology and operation · Question 57 of 60
Which statements about the evaluation and deployment functions of ML frameworks are correct?
3 answers are correct. Hard
Show answer
Answer
- C Some frameworks can convert models into formats for web, mobile, edge or embedded systems
- D For classification, frameworks can measure metrics such as accuracy, precision and recall
- E For ML regression, frameworks can determine error rates
Explanation
Frameworks offer tools to evaluate the model's performance on unseen data, for example accuracy, precision and recall for classification or error rates for regression. Some, but not all frameworks also support deployment, for example by converting the model into formats for web, mobile, edge or embedded systems. Evaluating on the training data alone would not show the performance on new data.