Wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

Neural Networks Quiz

Total questions: 10

Worksheet time: 5mins

Name
Class
Date
1.

What does the term 'hyperparameters' refer to in neural network training?

a)

Parameters that are learned during training

b)

The input values provided to the network

c)

Settings like the number of layers and nodes, which are set before training

d)

Super parameters that provide the best performance

e)

NN weights are hyperparameters as they are the most important in NNs

2.

Why might one choose to use a neural network instead of linear regression for a given dataset?

a)

Neural networks are always faster to train

b)

Neural networks can model complex, non-linear relationships better than linear regression

c)

Neural networks require less data

d)

Linear regression cannot be used for regression tasks

3.

In the context of neural networks, what does 'convergence' refer to?

a)

The point where the weights are randomly set

b)

The moment when the learning rate is maximized

c)

When the predicted output matches the actual output closely enough, stopping further updates

d)

When the number of hidden layers is increased

4.

Which of the following is NOT a typical application of deep learning?

a)

Self-Driving Cars

b)

News Aggregation

c)

Visual Recognition

d)

Simple Arithmetic Calculations

5.

Which of the following best describes the Gradient Descent algorithm?

a)

A method to increase the error between actual and predicted values

b)

An iterative process to update weights to minimize the error

c)

A technique to initialize weights randomly

d)

A process to normalize input data

6.

Given a non-linear regression problem , how can we use a neural network to solve it ?

a)

by adding more data

b)

use hyperparameters to reduce overfitting

c)

increase number of Hidden nodes

d)

increase number of layers

e)

Use a sigmoid function to provide non-linearity

7.

What is the primary function of a neuron in an artificial neural network?

a)

To store data

b)

To receive input and compute an output based on weighted sums

c)

To transmit data between layers

d)

To execute conditional statements

8.

In a single-layer perceptron, what is the role of the bias term (b)?

a)

It multiplies the input directly

b)

It acts as a threshold for activation

c)

It adds a constant value to the weighted sum

d)

It adjusts the learning rate

9.

What key concept allows deep learning models to perform tasks like language translation and image recognition effectively?

a)

Single-layer perceptrons

b)

Hand-coded feature extraction

c)

Multiple layers (depth) in the network

d)

High learning rates

10.

What is the primary difference between Stochastic Gradient Descent (SGD) and Batch Gradient Descent (BGD)?

a)

SGD updates weights after each instance, while BGD updates weights after all instances in the dataset

b)

SGD uses multiple layers, whereas BGD uses a single layer

c)

SGD is used for regression tasks, while BGD is used for classification tasks

d)

There is no significant difference between SGD and BGD