True$/$False:

Using a stochastic path through weight space in backpropagation allows for the energy

to increase in some updates.

When solving a $t=+1/-1$ problem in two dimensions using a decision boundary in

the form of a convex polygon, the resulting output problem is always linearly separable.

Increasing the number hidden neurons in the network increases the risk of overfitting.

Nesterov$`$s accelerated gradient scheme is often more efficient than the simple

momentum scheme because the weighting factor of the momentum term increases as a

function of iteration number.

Pruning increases the risk of overfitting.