Deep Learning Quiz

What is the loss function used in deep learning for regression?

• Mean Squared Error

• Cross Entropy

• Log Loss

• Mean Absolute Error

Which activation function is a straight-line function where the activation is proportional to the input?

• Linear Activation Function

• ReLU

• Tanh

• Sigmoid

What is the range of the Tanh activation function?

• [0, 1]

• [-1, 1]

• [0, ∞]

• [-∞, ∞]

What is the main advantage of Leaky ReLU over ReLU activation function?

• Solves the dying ReLU problem

• Enables backpropagation for negative input values

• Avoids vanishing gradient problem

• Less computationally expensive

What is the learning rate used in the example of regression?

• 0.8

• 0.05

• 0.2

• 0.1

What is the output value in the example of regression with input X1 = 2.6, X2 = 3.1, and weights w1 = 0.29, w2 = 0.24?

• 0.89

• 1.49

• 2.11

• 0.81

Which function is most commonly used as an activation function for the last layer of the neural network in multi-class classification?

• Sigmoid

• ReLU

• Softmax

• Tanh

What is the gradient descent algorithm used for in deep learning?

• Normalizing input data

• Updating weights randomly

• Calculating activation values

• Optimizing loss function

What is the main disadvantage of the Sigmoid activation function?

• Avoids vanishing gradient problem

• Output is not zero-centered

• Does not enable backpropagation

• Computationally expensive

What is the loss function used in deep learning for classification?

• Mean Absolute Error

• Cross Entropy

• Mean Squared Error

• Log Loss