AWS Certified Machine Learning – Specialty Set 6 Author: CloudVikas Published Date: 19 March 2020 Welcome to AWS Certified Machine Learning - Specialty Set 6. Please enter your email details to get QUIZ Details on your email id. Click on Next Button to proceed. 1. When analyzing a set of one-hot encoded data you realize that, while there is a massive amount of data, most of the values are absent. This is expected given the type of data, but what built-in SageMaker algorithm might you choose to work with this data?K-Nearest NeighborLinear LearnerFactorization Machines2. You are consulting with a retailer that wants to evaluate the sentiment of social media posts to determine if they are positive or negative. Which approach would be the most direct to this problem?Use BlazingText in Word2Vec mode for skip-gram.Use Object2Vec in sentiment detection mode.Use Amazon Comprehend.3. In what scenario is the DeepAR algorithm best suited?Determine the correlation between a person's diet and energy levels.Predict future sales of a new product based on historic sales of similar products.Decide whether to extend a credit card offer to a potential customer.4. You are consulting for a shipping company who wants to implement a very specific algorithm for shipping container optimization. The algorithm is not part of the currently available SageMaker built-in algorithms. What are your options? (Choose 2)Use a series of existing algorithms to simulate the actions of the unavailable algorithm.Post an incendiary message to Twitter hoping to shame AWS into adopting the specialized algorithm.Build the algorithm in a docker container and use that custom algorithm for training and inference in SageMaker.Search the AWS Marketplace for the algorithm. If it exists, deploy it using SageMaker for inferences.5. While using K-Means, what does it mean if we pass in k=4 as a hyperparameter?We want the algorithm to return the top 4 results.We want the algorithm to classify into 4 groups.We want the algorithm to group into 4 clusters.6. Which of the following is an example of unsupervised learning? (Choose 2)Using XGBoost to predict the selling price of a house in a particular market.Using Seq2Seq to extract a text string from a segment of a recorded speech.Using NTM to extract topics from a set of scientific journal articles.Using K-Means to cluster customers into demographic segments.7. Which of these examples would be considered as introducing bias into a problem space? (Choose 2) Failing to randomize a dataset even though you were told it was already random. Filtering out outliers in a dataset which are greater than 4 standard deviations outside the mean. Failing to randomize a dataset even though you were told it was already random. Removing records from a set of customer reviews that were not fully complete.8. To remove inconsistency in a process, you have created a very specific step-by-step process for patching servers. How would this best be described?The procedure is an algorithm as it will yield a consistent output.The procedure is a heuristic as it permits the person performing the upgrades from making unintended mistakes.The procedure is a heuristic as it will yield a consistent output.9. You have been asked to help develop a vision system for a manufacturing line that will reorient parts to a specific position using a robotic arm. What algorithm might you choose for the vision part of this problem?Semantic SegmentationObject DetectionObject2Vec10. You are on a personal quest to design the best chess playing model in the world. What might be a good strategy for this objective?Use a supervised learning strategy that is trained by feeding in the chess moves of thousands of famous chess experts.Use an unsupervised learning strategy to analyze similarities across thousands of the best chess matches.Use a reinforcement learning strategy to let the model learn itself.11. Which best describes SGD in common terms?Ensure that our sample size in a traffic study has at least 30 drivers.Seek to find the lowest point in elevation on a landscape.Calculate the linear distance between arrows shot into a target to determine accuracy.12. Which of the following might be used to focus a model on most relevant features?AQSXGBPCA13. Which of the following are good candidate problems for using XGBoost? (Choose 3) Map a text string to an n-gram vector. Deciding whether a transaction is fraudulent or not based on various details about the transaction. Create a policy that will guide an autonomous robot through an unknown maze. Providing a ranking of search results on an e-commerce site customized to a customer's past purchases. Evaluate handwritten numbers on a warranty card to detect what number they represent.14. You are being asked to develop a model to predict the likelihood that a student will pass a certification exam based on hours of study. Of the options given, what would be the best approach to this problem?Build a clustering mode with K-Means to group students who pass in a cluster.Build a Logistic Regression model using the hours of study as as a feature.Build a simulation-based model which will analyze past student performance at varying levels of study.15 out of 14Please fill in the comment box below. Author: CloudVikas
