wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

Mathematics in AI and ML- Five Days FDP of Emerging Trends in M

Total questions: 23

Worksheet time: 12mins

Name
Class
Date
1.

What does a derivative represent in the context of AI and ML?

a)

The total change over an interval

b)

The rate of change of a function at a given point

c)

The maximum value of a function

d)

The area under a curve

2.

What is the integral used for in AI and ML?

a)

Finding the rate of change

b)

Accumulating quantities over a range

c)

Minimizing a function

d)

Maximizing a function

3.

In gradient descent, what is the role of the learning rate (η)?

a)

It determines the size of the steps taken towards the minimum

b)

It identifies the global minimum

c)

It maximizes the loss function

d)

It eliminates the need for backpropagation

4.

What is the primary goal of the gradient descent algorithm?

a)

To find the maximum value of a function

b)

To find the minimum value of the cost function

c)

To increase the number of parameters

d)

To compute integrals

5.

Which of the following is a characteristic of convex optimization problems?

a)

Multiple local minima

b)

Only one local minimum which is also the global minimum

c)

Non-linear constraints

d)

Difficult to solve

6.

Which type of gradient descent updates parameters using a small batch of training examples?

a)

Batch Gradient Descent

b)

Stochastic Gradient Descent

c)

Mini-Batch Gradient Descent

d)

Recursive Gradient Descent

7.

Why is Lagrange multipliers used in optimization problems?

a)

To convert non-convex problems to convex ones

b)

To handle constraints in optimization problems

c)

To simplify linear problems

d)

To find the maximum value of a function

8.

What does the Lagrangian function combine?

a)

Objective function and constraints

b)

Variables and constants

c)

Gradient and Hessian

d)

Cost function and learning rate

9.

What is the purpose of backpropagation in neural networks?

a)

To initialize weights

b)

To update weights using the gradient of the loss function

c)

To compute the cost function

d)

To perform data preprocessing

10.

In gradient descent, what happens if the learning rate is too high?

a)

Convergence is too slow

b)

The algorithm may overshoot the minimum

c)

The gradient will vanish

d)

The cost function will become convex

11.

Which type of gradient descent uses the entire training dataset to update parameters?

a)

Stochastic Gradient Descent

b)

Batch Gradient Descent

c)

Mini-Batch Gradient Descent

d)

Recursive Gradient Descent

12.

What is the gradient in the context of optimization?

a)

The highest point of a function

b)

The rate of change of the cost function with respect to parameters

c)

The total area under the curve

d)

The average value of the function

13.

Why are non-convex optimization problems often used in machine learning?

a)

They are easier to solve

b)

They better capture complex real-world problems

c)

They guarantee global solutions

d)

They use less computational power

14.

Which of the following is a benefit of using Lagrange multipliers?

a)

They find the gradient of the objective function

b)

They simplify the problem by eliminating constraints

c)

They systematically handle constraints in optimization problems

d)

They maximize the loss function

15.

What is the primary goal of using Lagrange multipliers?

a)

To find the gradient of the objective function

b)

To handle optimization problems with constraints

c)

To simplify non-linear problems

d)

To convert non-convex problems to convex ones

16.

Which type of optimization problem is neural network training typically considered?

a)

Linear optimization

b)

Convex optimization

c)

Non-convex optimization

d)

Integer programming

17.

What is a common application of integrals in AI and ML?

a)

Finding the rate of change

b)

Computing probabilities and expectations

c)

Minimizing a function

d)

Maximizing a function

18.

What is the main challenge of using a high learning rate in gradient descent?

a)

It slows down convergence

b)

It may overshoot the global minimum

c)

It eliminates the need for backpropagation

d)

It ensures convergence

19.

Which of the following is a characteristic of non-convex optimization problems?

a)

A single global minimum

b)

Multiple local minima and maxima

c)

Linear constraints only

d)

Easy to solve

20.

What does the term "affine" mean in the context of constraints?

a)

Non-linear

b)

Linear

c)

Quadratic

d)

Exponential

21.

Which optimization method is used for training support vector machines?

a)

Linear programming

b)

Convex optimization

c)

Non-convex optimization

d)

Integer programming

22.

What is the significance of the Lagrangian function in optimization?

a)

It simplifies the objective function

b)

It combines the objective function with constraints

c)

It eliminates the need for constraints

d)

It finds the gradient of the constraints

23.

Which type of gradient descent updates parameters using a single training example?

a)

Batch Gradient Descent

b)

Stochastic Gradient Descent

c)

Mini-Batch Gradient Descent

d)

Recursive Gradient Descent