Deep Learning Quiz chap2

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

• Cross Entropy

• Mean Squared Error

• Sigmoid

• Mean Absolute Error

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

• ReLU

• Tanh

• Linear

• Sigmoid

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

• Controlling the magnitude of the vector update

• Determining the number of iterations

• Setting the number of layers in the neural network

• Adjusting the batch size

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

• ReLU

• Tanh

• Leaky ReLU

• Softmax

What is the range of the Tanh activation function?

• [0, 1]

• [-1, 1]

• [-∞, ∞]

• [0, ∞]

What is the derivative of the loss function with respect to the weights in a neural network?

• x(a-y)a(1-a)

• a-y

• a(1-a)x

• x(a-y)

Which function is used to avoid the vanishing gradient problem in deep learning?

• Tanh

• Leaky ReLU

• Sigmoid

• ReLU

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

• Mean Squared Error

• Cross Entropy

• Regression

• Mean Absolute Error

What is the output of the Softmax activation function for multi-class classification?

• Integer value

• Continuous value

• Binary output

• Vector of probability scores

What is the purpose of the learning rate in the gradient descent algorithm?

• Adjusting the loss function

• Setting the number of neurons in a layer

• Determining the activation function

• Controlling the step size of parameter updates