Fundamentals of ML and AIFull notesSummaryRingkasanStoriesPracticeMachine Learning Fundamentals11 exam-style questions on this lesson.Question 1 of 11A team's model performs poorly. Investigation shows the training data has many missing values, duplicate rows, and wrong labels. Which principle explains the result?AInference was run in batch modeBThe algorithm was too simpleCGarbage in, garbage outDThe model used too many hidden layersCheck answerQuestion 2 of 11Which order of steps matches the process of building an ML model?AChoose an algorithm, deploy, collect data, trainBTrain the model, collect data, choose an algorithm, evaluateCEvaluate, train, prepare data, choose an algorithmDCollect and prepare data, choose an algorithm, train, evaluate and iterateCheck answerQuestion 3 of 11A dataset contains photos, and each photo has a tag that says "cat" or "dog". What kind of data is this?ALabeled dataBReinforcement dataCTime series dataDUnlabeled dataCheck answerQuestion 4 of 11A factory records the temperature of each machine every minute. Which type of data is this?AUnlabeled image dataBStructured time series dataCUnstructured text dataDUnstructured image dataCheck answerQuestion 5 of 11. Select two.Which TWO are examples of unstructured data? (Select TWO.)ACustomer reviews posted on a websiteBA spreadsheet of monthly salesCA CSV file of customer ordersDPhotos uploaded by usersEA database table of product pricesCheck answer0 of 2 selectedQuestion 6 of 11A retailer has years of purchase data but no labels. It wants to discover groups of customers with similar buying habits. Which type of learning fits?ATransfer learningBReinforcement learningCUnsupervised learningDSupervised learningCheck answerQuestion 7 of 11A company trains a robot to walk across uneven ground. The robot gets a reward when it moves forward and a penalty when it falls. Which type of learning is this?ASupervised learningBSemi-supervised learningCUnsupervised learningDReinforcement learningCheck answerQuestion 8 of 11A hospital has 1 million X-ray images, but radiologists have labeled only 5,000 of them. The team wants to train on all the images. Which approach fits?ASemi-supervised learningBReinforcement learningCUnsupervised learning onlyDBatch inferencingCheck answerQuestion 9 of 11What is inferencing?ASplitting data into training and test setsBUsing a trained model to make predictions on new dataCChoosing the right algorithmDCollecting and labeling training dataCheck answerQuestion 10 of 11A company runs a model once a night over all of the day's sales records to produce a report for managers. Accuracy matters more than speed. Which inference type fits?AStreaming inferencing with sub-second latencyBReal-time inferencingCBatch inferencingDReinforcement inferencingCheck answerQuestion 11 of 11A customer support chatbot must reply to each message within a second. Which inference type fits?AOffline inferencingBBatch inferencingCSemi-supervised inferencingDReal-time inferencingCheck answerIntroduction7 exam-style questions on this lesson.Deep Learning Fundamentals6 exam-style questions on this lesson.