What is an optimization problem in the context of machine learning?

Minimizing or maximizing a function by systematically choosing input values

Finding the best way to sort data

What does the gradient of a function at a point represent?

The slope of the tangent line to the function at that point

The maximum value of the function

The total area under the function

The minimum value of the function

What does the gradient of a function at a point represent?

The slope of the tangent line to the function at that point

The maximum value of the function

The total area under the function

The minimum value of the function

What is the main purpose of converting color images to grayscale in CV applications?

To reduce computational complexity

To increase the image resolution

To enhance the image brightness

When is label encoding typically performed?

During data cleaning and preprocessing

What does One-Hot Encoding do?

Converts each category into a new column and assigns a 1 or 0

Assigns a unique identifier to each category

Encodes categories based on their frequency

Transforms categories into binary code

What is the main reason for encoding categorical data in machine learning models?

To convert categories into numerical values for model processing

To reduce computational resources needed

What does Mean Absolute Error (MAE) measure?

The average absolute difference between the predicted and actual values

The average squared difference between actual and predicted values

The square root of the mean squared error

The proportion of variance explained by the model

What is meant by "global minimum" in the context of optimization?

The point where the function has its lowest value on its domain

The lowest point in a specific region of the function

The point where the function value starts to increase

The highest point of the function

A key difference between Batch Normalization and traditional normalization methods is that Batch Normalization:

• C) Includes learning parameters that are optimized during training.

• B) Does not change the distribution of the data.

• D) Is applied only once before training starts.

Overfitting can be indicated by:

• B) High performance on training data and low performance on test data

• A) High performance on training data and high performance on test data

• C) Low performance on training data and low performance on test data

• D) Consistent performance on both training and test data

A significant advantage of deep learning in computer vision is:

A) Its ability to automatically learn complex features

B) Its reliance on linear feature representation

(C) Reduced computational requirements

(D) Simpler model architectures

The HSI color model separates image information into these components:

(D) Luminance, Chrominance (a & b)

In medical imaging, Poisson noise is frequently encountered due to:

(B) Errors in image compression algorithms

(A) The statistical nature of photons in sources like X-rays

(D) Interference from other electronic devices

When you enlarge an image without proper interpolation, the likely result is:

(c) Pixelation or blocky artifacts

which of the following describes the process of convolution with an image filter?

(B) Calculating weighted sums of pixel values within a moving window.

(A) Replacing each pixel with the average of its neighbors.

(C) Transforming the image from spatial to frequency domain. •

(D) Finding the maximum and minimum intensity values in an image.

Why does the first stage of Canny involve convolution with a blurring mask?

(B) To reduce the effects of noise

(C) To reduce the number of pixels

(D) To perform non-maximum suppression

. The primary purpose of the Sobel operator is to:

(C) Calculate image gradients for edge detection

Which gradient descent variant updates the parameters for each training example one at a time?

B) Stochastic Gradient Descent (SGD)

D) Momentum-based Gradient Descent

. What is meant by maximizing the objective function in an optimization problem?

B) Selecting the inputs that lead to the highest possible value of the objective function

A) Finding the solution with the highest computational cost

C) Increasing the number of constraints

D) Maximizing the number of inputs used

. Which of the following is NOT a way computers see images?

A) As a 2D matrix of pixel values

D) Through RGB channels for color images

In the context of computer vision, what does 'segmentation' refer to?

A) Dividing an image into multiple segments or pixels

B) Transforming the image into a grayscale format

C) Compressing the image for faster processing

D) Enhancing the brightness and contrast of the image

Which of the following is true about multilayer perceptrons (MLPs)?

C. They include hidden layers and can model complex datasets

A. They consist of a single layer of neurons

B. They are incapable of solving complex problems

D. They use only linear activation functions

What is the feedforward process in a neural network?

D. The process of calculating the output from input through hidden layers

A. The process of updating weights based on error

B. The process of backpropagating the error to update weights

C. The initial process of assigning weights to the neurons

In the context of neural networks, what is 'overfitting'?

A. When the model performs well on the training data but poorly on unseen data

B. When the model cannot fit the training data closely enough

C. When the model uses too many layers and neurons

D. When the model's weights are too large

Which of the following best describes the backpropagation process?

C. The process of updating weights based on the gradient of the error

A. The process of feeding inputs through the network

B. The process of calculating the weighted sum of inputs

D. The process of initializing the network's weights

What is a primary goal of exploratory data analysis (EDA)?

B) Understand the underlying patterns and anomalies in the data

A) Increase the size of the dataset

Which of the following best describes the purpose of using a validation set in machine learning?

C) To tune hyperparameters and avoid overfitting on the training set

A) To train the model with a subset of the data

B) To test the model's performance after deployment

D) To increase the size of the training dataset for better generalization

What is the main advantage of binary encoding over one-hot encoding?

B) It reduces dimensionality for high-cardinality features

A) It does not introduce multicollinearity

C) It assigns an inherent ordering

What does the F1 Score provide?

B) Balance between precision and recall

C) Total count of true positives

D) Difference between precision and recall

What is the main characteristic of linear activation functions also known as "no activation," or "identity function" (multiplied x1.0)?

C. They do not transform the input signal

• A. They output values only between 0 and 1

B. They can introduce nonlinearity into the model

In this diagram which we hand-drew in lecture, what do the horizontal axis (x-axis) and vertical axis (y-axis) represent?

A. x-axis is the amount of data, y-axis (vertical axis) is the performance of the algorithm

B. x-axis is the performance of the algorithm, y-axis (vertical axis) is the amount of data

C. x-axis is the amount of data, y-axis is the size of the model you train

D. x-axis is the input to the algorithm, y-axis is outputs

You are working on an automated check-out kiosk for a supermarket, and are building a classifier for apples, bananas and oranges. Suppose your classifier obtains a training set error of 0.5%, and a dev set error of 7%. Which of the following are promising things to try to improve your classifier? (Check all that apply.

A. Increase the regularization parameter lambda

B. Decrease the regularization parameter lambda

Why is the best mini-batch size usually not 1 and not m, but instead something in-between?

If the mini-batch size is 1, you lose the benefits of vectorization across examples in the minibatch.

If the mini-batch size is m, you end up with batch gradient descent, which has to process the whole training set before making progress.

If the mini-batch size is m, you end up with stochastic gradient descent, which is usually slower than mini-batch gradient descent.

If the mini-batch size is 1, you end up having to process the entire training set before making any progress.

Why is it important to carefully select the learning rate hyperparameter?

A) A too high learning rate may cause the model to converge too quickly to a suboptimal solution.

B) A too low learning rate might prevent the model from training entirely.

C) An inappropriate learning rate can cause the model to miss the global minimum or oscillate around it.

Mechatronics.M

Authored by Mahmoud Ashraf

Other

University

Used 4+ times

AI Actions

Add similar questions

Adjust reading levels

Convert to real-world scenario

Translate activity

More...

Content View

Student View

50 questions

Show all answers

MULTIPLE CHOICE QUESTION

2 mins • 1 pt

Changes in intensity across an image

Overall image brightness

Texture smoothness

Presence of noise

Access all questions and much more by creating a free account

Create resources

Host any resource

Get auto-graded reports

Continue with Google

Continue with Email

Continue with Classlink

Continue with Clever

or continue with

Microsoft

Apple

Others

Already have an account?

Similar Resources on Wayground

50 questions

JAMQUIZ '24 : 28.02.2024

Quiz

•

University

50 questions

Semi-Finals recorded

Quiz

•

9th Grade - University

55 questions

Môn Pháp Luật Đề 2 ^^

Quiz

•

University

50 questions

Steam Properties

Quiz

•

University - Professi...

50 questions

soal ANBK 2024

Quiz

•

5th Grade - University

45 questions

Módulo 1. Entrenamiento 3

Quiz

•

2nd Grade - University

50 questions

Manajemen Keuangan Syariah

Quiz

•

University

50 questions

League of Legends Quiz - Week 9 (Seth)

Quiz

•

KG - University

Popular Resources on Wayground

15 questions

Fractions on a Number Line

Quiz

•

3rd Grade

20 questions

Equivalent Fractions

Quiz

•

3rd Grade

25 questions

Multiplication Facts

Quiz

•

5th Grade

$fractions$

22 questions

fractions

Quiz

•

3rd Grade

20 questions

Main Idea and Details

Quiz

•

5th Grade

20 questions

Context Clues

Quiz

•

6th Grade

15 questions

Equivalent Fractions

Quiz

•

4th Grade

20 questions

Figurative Language Review

Quiz

•

6th Grade

Discover more resources for Other

12 questions

IREAD Week 4 - Review

Quiz

•

3rd Grade - University

23 questions

Subject Verb Agreement

Quiz

•

9th Grade - University

7 questions

Force and Motion

Interactive video

•

4th Grade - University

7 questions

Renewable and Nonrenewable Resources

Interactive video

•

4th Grade - University

5 questions

Poetry Interpretation

Interactive video

•

4th Grade - University

19 questions

Black History Month Trivia

Quiz

•

6th Grade - Professio...

15 questions

Review1

Quiz

•

University

15 questions

Pre1

Quiz

•

University

Mechatronics.M

Object recognition and image segmentation are primarily associated with:

Which image type is resolution-dependent, meaning it loses quality when enlarged?

The RGB color space is considered:

Which image transformation involves simply shifting the image along the x and/or y axes?

Which arithmetic operation is often used to enhance image contrast?

Which of the following is NOT a primary goal of image filtering?

The image gradient primarily indicates:

The first step in the Canny edge detection algorithm is typically:

What is an optimization problem in the context of machine learning?

What does the gradient of a function at a point represent?

Access all questions and much more by creating a free account

Similar Resources on Wayground

Popular Resources on Wayground

Discover more resources for Other