Font size
WorksheetsML_Office Hours_0828
Total questions: 10
Worksheet time: 6mins
What's the easiest way to store a real-time CSV data stream in Parquet format to S3?
Ingest CSV data using Apache Kafka Streams on Amazon EC2 instances and use Kafka Connect S3 to serialize data as Parquet.
Ingest CSV data from Amazon Kinesis Data Streams and use Amazon Glue to convert data to Parquet.
Ingest CSV data using Apache Spark structured streaming in an Amazon EMR cluster and use a PySpark to convert data into Parquet.
Ingest CSV data from Amazon Kinesis Data Streams and use Amazon Kinesis Data Firehose to convert data into Parquet
One column in your dataset is missing 25% of its data. What method could be used to reconstruct the missing data from adjacent columns?
Listwise deletion
Last observation carried forward
Multiple imputation
Mean substitution
A Data Scientist wants to gain real-time insights into a data stream of GZIP files. Which solution would allow the use of SQL to query the stream with the LEAST latency?
Amazon Kinesis Data Firehose to transform the data and put it into an Amazon S3 bucket.
Amazon Kinesis Data Analytics with an AWS Lambda function to transform the data
AWS Glue with a custom ETL script to transform the data
An Amazon Kinesis Client Library to transform the data and save it to an Amazon ES cluster
Your need to set up Kinesis Data Streams to process 100 transactions / second of a 100 KB payload. What minimum number of shards can you start with?
1 shard
10 shards
100 shards
1000 shards
Which method can be used to compare classification models against each other?
Recall
Misclassification rate
Mean absolute percentage error
Area under the ROC curve (AUC)
A Machine Learning Specialist has created a deep learning neural network model that performs well on the training data but performs poorly on the test data.
Which of the following methods should the Specialist consider using to correct this? (Select THREE.)
Decrease dropout.
Increase regularization
Increase feature combinations.
Decrease feature combinations.
Decrease regularization
How do you block all external access to SageMaker in a Private VPC subnet?
Place the Amazon SageMaker endpoint and S3 buckets within the same VPC
Use IAM policies to grant access to Amazon S3 and Amazon SageMaker
Ensure the VPC has S3 VPC endpoints and Amazon SageMaker VPC endpoints attached to it
Ensure the VPC has NAT gateway and associated security group allowing only outbound connections to Amazon S3 and SageMaker
How do you protect the training data so that it cannot be accessed and transferred to a remote host by malicious code accidentally installed in a container
Remove Amazon S3 access permissions from the SageMaker execution role
Encrypt the weights of the CNN model
Encrypt the training and validation dataset
Enable network isolation for training jobs
You need to create a model to detect if employees are wearing branded clothing while on the job in retail outlets. Which computer vision model should you choose?
Latent Direchlet allocation
Recurrent neural network
K-Means
Convolutional Neural Network
A Machine Learning Specialist built an image classification deep learning model. However the Specialist ran into an overfitting problem in which the training and testing accuracies were 99% and 75%r respectively.
How should the Specialist address this issue and what is the reason behind it?
The learning rate should be increased because the optimization process was trapped at a local minimum.
The dimensionality of dense layer next to the flatten layer should be increased because the model is not complex enough.
The epoch number should be increased because the optimization process was terminated before it reached the global minimum.
The dropout rate at the flatten layer should be increased because the model is not generalized enough.
