A.tensor

B.grid

C.calculation graph

D.dot product

A.Backpropagation can only be used in feedforward neural networks

B.Back propagation refers to the back propagation of errors through the network

C.Backpropagation passes through the activation function

D.Backpropagation can be combined with gradient descent algorithm to update network weights

A.False

B.True

A.Can be used to process sequence data.

B.Unlike convolutional neural networks. parameters of RNN cannot be shared

C.Cannot process variable length sequence data.

D.The units above the hidden layer are not associated With each other.

A.PaleyFunction

B.Infinity

C.DistBelief

D.ConvexOne