Gradient Descent Method

In deep learning, the gradient descent method aims to minimize a given loss function of the neural network.

• True

• False

The loss function for linear regression is the Cross-Entropy.

• True

• False

Gradient descent always converges to some global minimum.

• True

• False

The learning rate determines the step size at each iteration while moving toward a minimum of a loss function.

• True

• False

In batch gradient descent, we consider one example at a time to update the current weight and bias values.

• True

• False

A one-neuron perceptron can classify two classes of objects.

• True

• False

Logistic regression is a classification model.

• True

• False

The loss function for logistic regression is the Squared Error.

• True

• False

Logistic regression transforms its output using the Tanh function to return a probability value.

• True

• False

Logistic regression predicts the probability of the occurrence of a binary outcome.

• True

• False