Which of the following is not an AI research area ()?
A. Machine certification
B. Pattern recognition
C. Artificial life
D. Compilation principle
查看答案
The purpose of artificial intelligence is to allow machines to ()to achieve the mechanization of certain mental work.
A. be smart
B. work like a person
C. completely replace the human brain
D. simulate, extend and expand human intelligence
In order to solve the problem of how to simulate human perceptual thinking, such as visual understanding, intuitive thinking, perception, etc., researchers find an important mechanism of information processing is ()
A. expert system
B. artificial neural network
C. pattern recognition
D. intelligent agent
The wrong statement about the common methods of transfer learning is ()
A. The sample-based transfer learning method is simple and easy to implement, so it is currently the most adopted method
B. Feature selection and transformation based on feature-based transfer learning can achieve better results
C. The advantage of model-based transfer learning is that there are similarities in model building, which can be used
D. The disadvantage of model-based transfer learning is that the model parameters are not easy to converge Explanation: The weight selection and similarity measurement of sample-based transfer learning depend on experience, and the data distribution of the source and target domains are often different. The most commonly used method is feature-based transfer learning.
Inductive reasoning is a reasoning ()
A. From general to individual
B. From individual to general
C. From individual to individual
D. From general to general