A.False

B.True

A.The latter model must be built on top of the previous model

B.Additive relationship

C.Independent

D.relationship

A.manifold learning

B.feature engineering

C.dimension disaster

D.local invariance and smooth regularization

A.TRUE

B.FALSE

A.Back-propagation stage sends training input to the network to obtain stimulus response

B.The learning process of the backpropagation algorithm consists of the forward propagation process and the back propagation process

C.Backpropagation algorithm mainly consists of two links (incentive propagation, weight update) iteratively iterate until the target range of the network's response to the input

D.Back propagation algorithm is suitable for a learning algorithm of multi-layer neural network, which is based on the gradient descent method