
Neural Networks Quiz
Authored by Usman Ali
Information Technology (IT)
University

AI Actions
Add similar questions
Adjust reading levels
Convert to real-world scenario
Translate activity
More...
Content View
Student View
10 questions
Show all answers
1.
MULTIPLE CHOICE QUESTION
30 sec • 1 pt
A simple Multi-Layer Perceptron (MLP) without any non-linear activation functions is mathematically equivalent to:
A universal function approximator.
A single, wider linear layer.
A model incapable of learning.
A support vector machine with a linear kernel.
2.
MULTIPLE CHOICE QUESTION
30 sec • 1 pt
The primary motivation for using the ReLU activation function over Sigmoid in deep hidden layers is to:
Ensure the output is always positive.
Confine the activation values between 0 and 1.
Mitigate the vanishing gradient problem.
Make the network more computationally expensive but more accurate.
3.
MULTIPLE CHOICE QUESTION
30 sec • 1 pt
The "dying ReLU" problem is characterized by:
A neuron's weights being updated such that its pre-activation input is consistently negative, causing its output and gradient to be zero.
The network becoming too deep, causing all ReLU activations to eventually become zero.
The learning rate being too low, preventing weights from being updated.
A neuron's weights exploding to infinity.
4.
MULTIPLE CHOICE QUESTION
30 sec • 1 pt
Why is breaking symmetry by initializing weights randomly (e.g., using Xavier or He initialization) crucial for training?
It guarantees faster convergence to the global minimum.
It prevents all neurons in a layer from learning the same features, as they would with zero initialization.
It acts as a form of L2 regularization.
It ensures the initial loss of the network is exactly 1.0.
5.
MULTIPLE CHOICE QUESTION
30 sec • 1 pt
What is the primary purpose of the bias term in a neuron?
To scale the output of the activation function.
To act as a learnable offset, allowing the activation function to be shifted left or right.
To prevent the weights from becoming zero during training.
To control the learning rate for that specific neuron.
6.
MULTIPLE CHOICE QUESTION
30 sec • 1 pt
The Universal Approximation Theorem suggests that:
Any neural network can solve any problem.
A single-layer perceptron can approximate any linear function.
A feed-forward network with one hidden layer and a non-linear activation can approximate any continuous function to arbitrary precision.
Deeper networks are always better than wider networks.
7.
MULTIPLE CHOICE QUESTION
30 sec • 1 pt
A model is exhibiting high variance and low bias. This is a classic case of:
Underfitting, where the model is too simple for the data.
Overfitting, where the model has learned the training data too well, including its noise.
A well-generalized model.
A model trained with an incorrect loss function.
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
%20(1).png)
Apple
Others
Already have an account?
Similar Resources on Wayground
10 questions
Python_Quiz_1
Quiz
•
University
15 questions
Introduction to Programming
Quiz
•
University
15 questions
P3 IAS 2 Quiz
Quiz
•
University
10 questions
OOP-Q1
Quiz
•
University
10 questions
Melaka 2024
Quiz
•
University
12 questions
CLC Lesson 4&5 Quiz
Quiz
•
University
12 questions
Java_Quiz_Part_2
Quiz
•
University
15 questions
Emp. Tech. 12 - Intro to MS Excel Quiz
Quiz
•
12th Grade - University
Popular Resources on Wayground
8 questions
Spartan Way - Classroom Responsible
Quiz
•
9th - 12th Grade
15 questions
Fractions on a Number Line
Quiz
•
3rd Grade
14 questions
Boundaries & Healthy Relationships
Lesson
•
6th - 8th Grade
20 questions
Equivalent Fractions
Quiz
•
3rd Grade
3 questions
Integrity and Your Health
Lesson
•
6th - 8th Grade
25 questions
Multiplication Facts
Quiz
•
5th Grade
9 questions
FOREST Perception
Lesson
•
KG
20 questions
Main Idea and Details
Quiz
•
5th Grade
Discover more resources for Information Technology (IT)
20 questions
Disney Trivia
Quiz
•
University
7 questions
Fragments, Run-ons, and Complete Sentences
Interactive video
•
4th Grade - University
7 questions
Renewable and Nonrenewable Resources
Interactive video
•
4th Grade - University
10 questions
DNA Structure and Replication: Crash Course Biology
Interactive video
•
11th Grade - University
7 questions
Force and Motion
Interactive video
•
4th Grade - University
20 questions
Implicit vs. Explicit
Quiz
•
6th Grade - University
14 questions
Ch.3_TEACHER-led
Quiz
•
University
7 questions
Comparing Fractions
Interactive video
•
1st Grade - University