The core idea of generative confrontation network is dualism and game in game theory.（ ）

问答题

The idea of boosting algorithm originated from the probabilistic approximately correct (PAC) learning model. It was proposed by American scientist Kearns and British scientist valiant in 1980s, and valiant won the Turing Award in 2010.（ ）

单选题

The menu property bar has "label" and "tag". The label is equivalent to the tag value of the menu item, and the tag is the name of the menu display.（ ）

单选题

A GAN mainly includes a generator G and a discriminator D. （ ）

单选题

When the window event occurs, the main event loop will respond and assign the appropriate event handler to the window event. （ ）

问答题

Among many deep learning algorithms, deep convolutional neural network (DCNN) should be one of the most widely studied, widely used and representative algorithms.（ ）

单选题

SOFM neural networks are different from other artificial neural networks in that they adopt competitive learning rather than backward propagation error correction learning method similar to gradient descent, and in a sense, they use neighborhood functions to preserve topological properties of input space. （ ）

单选题

Neurons are highly polarized cells, which are mainly composed of two parts: the cell body and the synapse. （ ）

单选题

The main purpose of adding regularization term into the formula of calculating strong classifier is to prevent the over fitting of AdaBoost algorithm, which is usually called step size in algorithm. （ ）

单选题

The determinant changes sign when two rows (or two columns) are exchanged. The value of determinant is zero when two rows (or two columns) are same. （ ）

单选题

Elman neural network is a kind of dynamic recurrent network, which can be divided into full feedback and partial feedback. In the partial recurrent network, the feedforward connection weight can be modified, and the feedback connection is composed of a group of feedback units, and the connection weight cannot be modified. （ ）

单选题

In 1974, Paul Werbos of the natural science foundation of the United States first proposed the use of error back propagation algorithm to train artificial neural networks in his doctoral dissertation of Harvard University, and deeply analyzed the possibility of applying it to neural networks, effectively solving the XOR loop problem that single sensor cannot handle. （ ）

单选题

The neuron model can be divided into three parts: input module, transfer function and output module. （ ）

单选题

The perceptron learning algorithm is driven by misclassification, so the stochastic gradient descent method is used to optimize the loss function. （ ）

单选题

VGGNet is composed of two parts: the convolution layer and the full connection layer, which can be regarded as the deepened version of AlexNet. （ ）

单选题

The basic idea of RBF neural network is to use radial basis function as the "basis" of hidden layer hidden unit to form hidden layer space, and hidden layer transforms input vector. The input data transformation of low dimensional space is mapped into high-dimensional space, so that the problem of linear separability in low-dimensional space can be realized in high-dimensional space. （ ）

单选题

In practical application, the inverse of the correlation matrix and the correlation coefficient are not easy to obtain, so the approximate steepest descent method is needed in the algorithm design. The core idea is that the actual mean square error of the network is replaced by the mean square error of the k-th iteration.（ ）

单选题

At present, researchers have successfully applied Hopfield neural network to solve the traveling salesman problem (TSP), which is the most representative of optimization combinatorial problems. （ ）

单选题

Prediction and evaluation is an activity of scientific calculation and evaluation of some characteristics and development status of things or events in the future according to the known information of objective objects. （ ）