The similarities between neural network and deep learning are ()
A. The system consists of input layer, hidden layer (multilayer) and output layer. Only the adjacent nodes are connected. Each layer can be regarded as a logistic regression model.
Both of them use BP algorithm to adjust the parameters, that is, using iterative algorithm to train the whole network.
C. During the training, the initial value is set randomly, the output of the current network is calculated, and then the parameters of the previous layers are changed according to the difference between the current output and the real label of the sample until convergence.
D. For a deep network (more than 7 layers), there will be gradient diffusion.
查看答案
() does not belong to the field of digital image processing
A. Industrial testing
B. Physical discovery
C. Biomedicine
D. Identification of biological characteristics
In the following options, the three points that do not belong to the state space method are ()
A. State
B. Operator
C. State space method
D. Nodes and arcs or chains
What is not difficult for reinforcement learning is the excessive sample size ()
A. High state and behavior dimensions
B. Large error of state information
C. Excessive sample size
D. Model limitations
The formation process of feature vectors includes:()
A. Feature formation
B. feature extraction
C. Feature selection
D. feature evaluation
微信支付 
支付宝支付