WorksheetsMathematics in AI and ML- Five Days FDP of Emerging Trends in M
Total questions: 23
Worksheet time: 12mins
What does a derivative represent in the context of AI and ML?
The total change over an interval
The rate of change of a function at a given point
The maximum value of a function
The area under a curve
What is the integral used for in AI and ML?
Finding the rate of change
Accumulating quantities over a range
Minimizing a function
Maximizing a function
In gradient descent, what is the role of the learning rate (η)?
It determines the size of the steps taken towards the minimum
It identifies the global minimum
It maximizes the loss function
It eliminates the need for backpropagation
What is the primary goal of the gradient descent algorithm?
To find the maximum value of a function
To find the minimum value of the cost function
To increase the number of parameters
To compute integrals
Which of the following is a characteristic of convex optimization problems?
Multiple local minima
Only one local minimum which is also the global minimum
Non-linear constraints
Difficult to solve
Which type of gradient descent updates parameters using a small batch of training examples?
Batch Gradient Descent
Stochastic Gradient Descent
Mini-Batch Gradient Descent
Recursive Gradient Descent
Why is Lagrange multipliers used in optimization problems?
To convert non-convex problems to convex ones
To handle constraints in optimization problems
To simplify linear problems
To find the maximum value of a function
What does the Lagrangian function combine?
Objective function and constraints
Variables and constants
Gradient and Hessian
Cost function and learning rate
What is the purpose of backpropagation in neural networks?
To initialize weights
To update weights using the gradient of the loss function
To compute the cost function
To perform data preprocessing
In gradient descent, what happens if the learning rate is too high?
Convergence is too slow
The algorithm may overshoot the minimum
The gradient will vanish
The cost function will become convex
Which type of gradient descent uses the entire training dataset to update parameters?
Stochastic Gradient Descent
Batch Gradient Descent
Mini-Batch Gradient Descent
Recursive Gradient Descent
What is the gradient in the context of optimization?
The highest point of a function
The rate of change of the cost function with respect to parameters
The total area under the curve
The average value of the function
Why are non-convex optimization problems often used in machine learning?
They are easier to solve
They better capture complex real-world problems
They guarantee global solutions
They use less computational power
Which of the following is a benefit of using Lagrange multipliers?
They find the gradient of the objective function
They simplify the problem by eliminating constraints
They systematically handle constraints in optimization problems
They maximize the loss function
What is the primary goal of using Lagrange multipliers?
To find the gradient of the objective function
To handle optimization problems with constraints
To simplify non-linear problems
To convert non-convex problems to convex ones
Which type of optimization problem is neural network training typically considered?
Linear optimization
Convex optimization
Non-convex optimization
Integer programming
What is a common application of integrals in AI and ML?
Finding the rate of change
Computing probabilities and expectations
Minimizing a function
Maximizing a function
What is the main challenge of using a high learning rate in gradient descent?
It slows down convergence
It may overshoot the global minimum
It eliminates the need for backpropagation
It ensures convergence
Which of the following is a characteristic of non-convex optimization problems?
A single global minimum
Multiple local minima and maxima
Linear constraints only
Easy to solve
What does the term "affine" mean in the context of constraints?
Non-linear
Linear
Quadratic
Exponential
Which optimization method is used for training support vector machines?
Linear programming
Convex optimization
Non-convex optimization
Integer programming
What is the significance of the Lagrangian function in optimization?
It simplifies the objective function
It combines the objective function with constraints
It eliminates the need for constraints
It finds the gradient of the constraints
Which type of gradient descent updates parameters using a single training example?
Batch Gradient Descent
Stochastic Gradient Descent
Mini-Batch Gradient Descent
Recursive Gradient Descent
