Search Header Logo

ANNS-06

Authored by Megyeri István

Information Technology (IT)

University

Used 7+ times

ANNS-06
AI

AI Actions

Add similar questions

Adjust reading levels

Convert to real-world scenario

Translate activity

More...

    Content View

    Student View

6 questions

Show all answers

1.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Overfitting: the model learns not only the [] features but also the [] patterns of the finite dataset

general - large

general - strange

small - large

small - strange

2.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

By [] the model’s size (complexity), the flexibility [], so it will become more accurate on training examples

increasing - decreases

  • decreasing - decreases

increasing - increases

  • decreasing - increases

3.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

overfitting generally occurs near the [] of training by backpropagation

second quarter

middle

begining

end

4.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

[] regularizes the network by modifying the loss function

Weight decay

Dropout

Ensemble

noise injection

5.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Dropout drops certain [] according to a random probability.

inputs

neurons

weights

output neurons

6.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Which technique helps to prevent overfitting by combining multiple models?

Batch Normalization

Data Augmentation

Ensemble Learning

Dropout

Access all questions and much more by creating a free account

Create resources

Host any resource

Get auto-graded reports

Google

Continue with Google

Email

Continue with Email

Classlink

Continue with Classlink

Clever

Continue with Clever

or continue with

Microsoft

Microsoft

Apple

Apple

Others

Others

Already have an account?