The following statements about neural networks and deep learning are correct()
A. Both use a layered structure. The system includes a multi-layer network composed of an input layer, a hidden layer (multi-layer), and an output layer. Only nodes in adjacent layers are connected, and nodes in the same layer and cross-layers are not connected to each other. , Each layer can be regarded as a logistic regression model.
B. Uses the BP algorithm to adjust the parameters, that is, iterative algorithm to train the entire network. Randomly set the initial value, calculate the output of the current network, and then change the parameters of the previous layers according to the difference between the current output and the true label of the sample until convergence
C. Adopts layer-by-layer training mechanism The reason for adopting this mechanism is that if the BP mechanism is adopted, for a deep network (more than 7 layers), the residual propagation to the front most layer will become very small, and the so-called gradient diffusion occurs.
D. Its advantage lies in that it can realize complex function approximation and characterize the distributed representation of input data by learning a deep nonlinear network structure.
The reason why deep neural networks in deep learning generally do not use the BP algorithm is ()
A. During feedback adjustment, the gradient becomes more and more sparse, and the error correction signal becomes smaller and smaller from the top layer
B. Convergence is easy to the local minimum, because it is initialized with random values, it is easy to cause this situation when the initial value is far from the optimal region
C. BP algorithm requires labeled data to train, but most of the data is unlabeled
Deep learning clearly highlights the importance of feature learning. By layer-by-layer feature transformation, the feature representation of the sample in the original space is transformed into a new feature space, thereby making classification or prediction easier. Compared with the method of artificially constructing features, using big data to learn features is abler to characterize the rich internal information of the data
The following statements about artificial intelligence and machine intelligence are correct()
A. The dependent carrier of artificial intelligence is a machine, just like humans and animals have a body, the machine is the "body" of artificial intelligence. A machine with a "body" will have a variety of perception, cognition, language, behavior, etc. like humans or animals. Of intelligence
B. Compared to human or animal intelligence, machine intelligence is not created by natural evolution, but artificially created;
C. From the perspective of the intelligent generation mechanism of humans and machines, machines rely on unnatural mechanisms to produce intelligence and even wisdom different from humans.
D. Non-natural intelligence or non-biological intelligence is called artificial intelligence. Compared with natural intelligence, non-living intelligence realized by using machines made or invented by humans is called machine intelligence.
The following statement is correct()
Artificial intelligence is a computer program that makes reasonable actions based on the perception of the environment and obtains the greatest benefits
B. Any computer into rough has artificial intelligence
C. For specific tasks, artificial intelligence programs have the ability to learn independently
D. Artificial intelligence programs and humans have the same way of thinking
The main methods of brain-like computing are()
A. Development of neuromorphic models based on the principle of biological neurons
B. Using new electronic components mersister to simulate biological neurons
C. Development of virtual artificial brain based on brain science big data
Design a brain-like model based on a known brain function model
E. Simulate human brain intelligence based on deep learning technology
微信支付 
支付宝支付