NLP_4

What is the primary purpose of an activation function in a neural network?

• A) To initialize the weights
• B) To calculate the loss
• C) To introduce non-linearity
• D) To perform gradient descent

In gradient descent, what does the learning rate control?

• A) The size of the weight updates
• B) The number of layers in the network
• C) The number of training examples
• D) The activation function used

Which loss function is commonly used for regression problems in neural networks?

• A) Cross-Entropy Loss
• B) Mean Squared Error (MSE)
• C) Categorical Cross-Entropy Loss
• D) Sigmoid Loss

What is the primary role of the Chain Rule in neural network training?

• A) Initializing weights
• B) Calculating gradients
• C) Determining the learning rate
• D) Choosing the activation function

What does the softmax activation function do in multi-class classification?

• A) Introduces non-linearity to smooth the Loss function

• B) Converts output of last hidden layer into probabilities

• C) Calculates the mean squared error
• D) Determines the learning rate

What does the term "Black Box" refer to in the context of neural networks?

• A) A network with no hidden layers is called a black box

• B) The output layer of a network
• C) A network with no activation functions
• D) NN are not easily interpretable nor explainable

In a neural network with multiple layers, what is the purpose of the Chain Rule when computing gradients?

• It simplifies the loss function
• B) It ensures convergence to a global minimum
• C) It calculates Gradients through backpropagation

• D) It prevents overfitting by adding regularization terms

Given a binary classification problem where the true label is 1 and the predicted probability is 0.7, what is the Cross-Entropy Loss?

• A) log(0.3)

• B) -log(0.3)

• C) log(0.7)

• D) -log(0.7)

In a multi-class classification problem with three classes (Class A, Class B, and Class C), if the true label is Class C and the predicted probabilities are [0.2, 0.7, 0.1], what is the Categorical Cross-Entropy Loss?

• A) log(0.1)

• B) -log(0.9)

• C) log(0.2)

• D) -log(0.1)

• 3.2
• 6.4
• 4.8
• 0.8