Free MLS-C01 Exam Braindumps (page: 21)

Page 21 of 84

A Data Scientist is training a multilayer perception (MLP) on a dataset with multiple classes. The target class of interest is unique compared to the other classes within the dataset, but it does not achieve and acceptable recall metric. The Data Scientist has already tried varying the number and size of the MLP’s hidden layers, which has not significantly improved the results. A solution to improve recall must be implemented as quickly as possible.

Which techniques should be used to meet these requirements?

  1. Gather more data using Amazon Mechanical Turk and then retrain
  2. Train an anomaly detection model instead of an MLP
  3. Train an XGBoost model instead of an MLP
  4. Add class weights to the MLP’s loss function and then retrain

Answer(s): D


Reference:

https://androidkt.com/set-class-weight-for-imbalance-dataset-in-keras/



A Machine Learning Specialist works for a credit card processing company and needs to predict which transactions may be fraudulent in near-real time. Specifically, the Specialist must train a model that returns the probability that a given transaction may fraudulent.

How should the Specialist frame this business problem?

  1. Streaming classification
  2. Binary classification
  3. Multi-category classification
  4. Regression classification

Answer(s): B



A real estate company wants to create a machine learning model for predicting housing prices based on a historical dataset. The dataset contains 32 features.

Which model will meet the business requirement?

  1. Logistic regression
  2. Linear regression
  3. K-means
  4. Principal component analysis (PCA)

Answer(s): B



A Machine Learning Specialist is applying a linear least squares regression model to a dataset with 1,000 records and 50 features. Prior to training, the ML Specialist notices that two features are perfectly linearly dependent.

Why could this be an issue for the linear least squares regression model?

  1. It could cause the backpropagation algorithm to fail during training
  2. It could create a singular matrix during optimization, which fails to define a unique solution
  3. It could modify the loss function during optimization, causing it to fail during training
  4. It could introduce non-linear dependencies within the data, which could invalidate the linear assumptions of the model

Answer(s): B



Page 21 of 84



Post your Comments and Discuss Amazon MLS-C01 exam with other Community members:

Richard commented on October 24, 2023
i am thrilled to say that i passed my amazon web services mls-c01 exam, thanks to study materials. they were comprehensive and well-structured, making my preparation efficient.
Anonymous
upvote

Richard commented on October 24, 2023
I am thrilled to say that I passed my Amazon Web Services MLS-C01 exam, thanks to study materials. They were comprehensive and well-structured, making my preparation efficient.
Anonymous
upvote

Ken commented on October 13, 2021
I would like to share my good news with you about successfully passing my exam. This study package is very relevant and helpful.
AUSTRALIA
upvote

Alex commented on April 19, 2021
A very great in amount of questions are from real exam. Almost same wording. :)
SOUTH KOREA
upvote

MD ABU S CHOWDHURY commented on January 18, 2020
Working on the test..
UNITED STATES
upvote