() is false statement about BP neural network.
A. BP network is a kind of feed-forward network, whose hidden elements must be layered, also known as multi-layer feed-forward network.
B. The purpose of back propagation is to modify the weights of neurons in each layer to minimize error signals.
C. Forward propagation is the transmission of input information from the input layer to the hidden layer and finally to the output layer.
D. The three core parts of d. BBP neural network learning algorithm are weight adjustment, output layer connection weight adjustment and hidden layer connection weight adjustment.
() is a typical fuzzy inference method
A. Takagi-Mamdani fuzzy inference method
B. Takagi-Larsen fuzzy inference method
C. Takagi-Zadeh fuzzy inference method
D. Takagi-Sugeno fuzzy inference method
The following statement is wrong ()
A. Big data belongs to batch analysis.
Big data, real-time analysis rather than batch analysis.
C. Data in big data interact frequently.
D. The value density of big data is low.
E. In big data analysis, not using random samples, but using all data for analysis.
The following statement is wrong ()
A. ‘Grid cells’ are located in the blue area of the hippocampus. When the animal reaches a specific position in the area, a single grid cell is activated, and these positions are arranged in a six deformation pattern.
B. The separation representation of robot's direction and position is not suitable for mapping and navigation in a large and uncertain environment. At present, the problem of separation of position and position has not been solved.
C. According to the activity of road signs and location cells, each step of the gating selection model proposed by the robot intelligent research system needs to get the next step direction, and select the final movement direction according to the winner's taking all.
D. Boston University UM.Erdem and Michael Hasselmo put forward the linear predictive trajectory model, which is based on the forward planning path of head direction cell, continuous pulse cell, grid cell and position cell.
The mistake in the following statement about machine learning is ( )
A. Deep learning is a learning method based on unsupervised feature learning and feature hierarchy.
B. In machine learning, getting good features is the key to successful recognition.
C. The training process of deep learning is mainly divided into two steps: the first step, top-down supervised learning; the second step, top-down unsupervised learning.
Deep learning adopts layer by layer training mechanism.