AWS Machine Learning - Specialty Official Practice Question Set (MLS-C01) v2

Pre-splitting Your Data

Used for when you need explicit control over the data in your training and evaluation datasources.

Sequentially Splitting Your Data

This approach is useful if you want to evaluate your ML models on data for a certain date or within a certain time range

Randomly Splitting Your Data

This approach is useful to ensure that the distribution of the data is similar in the training and evaluation datasources.

True

Is important to use the same seed string value for both datasources and the complement flag for one datasource

True

A common pitfall in developing a high-quality ML model is evaluating the ML model on data that is not similar to the data used for training.

True

The model and evaluation are too dissimilar (have extremely different descriptive statistics) to be useful.

This can happen when input data is sorted by one of the columns in the dataset

and then split sequentially.

False

You need to use random splitting in Amazon ML if you have already randomized your input data

groupFiles

Set _ to inPartition to enable the grouping of files within an Amazon S3 data partition.

groupSize

Set _ to the target size of groups in bytes.

False

The groupSize property is required

recurse

Set _ to True to recursively read files in all subdirectories when specifying paths as an array of paths.

False

You need to set recurse if paths is an array of object keys in Amazon S3

Sequence-to-Sequence Algorithm

supervised learning algorithm where the input is a sequence of tokens (for example

Sequence-to-Sequence Algorithm

Algorithm to use for a:

machine translation

Sequence-to-Sequence Algorithm

Algorithm to use for a:

text summarization

True

Amazon SageMaker AI seq2seq uses Recurrent Neural Networks (RNNs) models

False

Amazon SageMaker AI seq2seq does not use Convolutional Neural Network (CNN) models

Data Flow

Create a _ to define a series of ML data prep steps.

Used to combine datasets from different data sources

identify the number and types of transformations you want to apply to datasets

Transform

Clean and your dataset using standard s like string

Examples in usage:

• text and date/time embedding
• categorical encoding.

Generate Data Insights

Automatically verify data quality and detect abnormalities in your data with Data Wrangler Data Quality and Insights Report.

True

Amazon SageMaker Canvas supports training a range of model types

Amazon SageMaker Canvas

Canvas custom model on the following types of datasets:

• Tabular (including numeric

categorical

Numeric prediction

Predicting house prices based on features like square footage

Numeric

Local upload

Amazon S3

2 category prediction

Predicting whether or not a customer is likely to churn

Binary or categorical

Local upload

Amazon S3

3+ category prediction

Predicting patient outcomes after being discharged from the hospital

Categorical

Local upload

Amazon S3

Time series forecasting

Predicting your inventory for the next quarter

Timeseries

Local upload

Amazon S3

Single-label image prediction

Predicting types of manufacturing defects in images

Image (JPG

PNG)

Local upload

Amazon S3

Multi-category text prediction

Predicting categories of products

Target column: binary or categorical

Local upload

Amazon S3

True

In Amazon ML

Area Under the (Receiver Operating Characteristic) Curve (AUC)

Amazon ML provides an industry-standard accuracy metric for binary classification models called _

True

AUC values near 1 indicate an ML model that is highly accurate.

True

Values near 0.5 indicate an ML model that is no better than guessing at random.

True

Values near 0 are unusual to see