Developing ML solutionsFull notesSummaryRingkasanStoriesPracticeSources of ML Models7 exam-style questions on this lesson.Question 1 of 7A company wants to add an ML model to its application with the least effort and the lowest operational overhead. Which source fits?AA pre-trained model from SageMaker JumpStartBScript mode with PyTorchCA model trained from scratchDA custom Docker imageCheck answerQuestion 2 of 7A data scientist has training code written in scikit-learn and wants to run it on SageMaker without building a container. Which option fits?AAWS DeepRacerBScript mode with a supported frameworkCSageMaker CanvasDCustom Docker imagesCheck answerQuestion 3 of 7A team needs specific packages that no pre-made SageMaker image includes. Which option fits?AScript modeBSageMaker JumpStartCA custom Docker imageDBuilt-in algorithmsCheck answerQuestion 4 of 7Which is the correct order of model sources from least to most effort?ABuilt-in algorithms, pre-trained models, custom Docker images, script modeBCustom Docker images, script mode, built-in algorithms, pre-trained modelsCScript mode, pre-trained models, custom Docker images, built-in algorithmsDPre-trained models, built-in algorithms, script mode, custom Docker imagesCheck answerQuestion 5 of 7. Select two.Which TWO are features of SageMaker JumpStart? (Select TWO.)APre-trained open-source models you can deploy, fine-tune, and evaluateBProduction drift monitoringCSolution templates that set up infrastructure for common use casesDA drag-and-drop no-code ML builderEHuman labeling workforcesCheck answer0 of 2 selectedQuestion 6 of 7Which problem types do SageMaker built-in algorithms cover?ASupervised, unsupervised, image, time series, and text problemsBOnly generative AI and foundation modelsCOnly image processing and computer visionDOnly regression on tabular dataCheck answerQuestion 7 of 7Why would a team choose SageMaker built-in algorithms over writing its own?AThey only run on premises, not in the AWS cloudBThey are designed to scale to large datasets and significant computeCThey require you to build custom Docker imagesDThey can't be trained on your own labeled dataCheck answerDeveloping ML Solutions with Amazon SageMaker AI10 exam-style questions on this lesson.Machine Learning Models Performance Evaluation12 exam-style questions on this lesson.