Overview / Usage

　　The summary of the thesis is that the artificial intelligence mathematical model is mainly used today, which is based on the application of neural networks. Therefore, based on the above premise, it can be learned that artificial intelligence mainly applies mathematical theory. The three theories of constructing this neural network are probability theory. Heisenberg's uncertainty theorem and fractal theory are the basis.

　　Therefore, it is confirmed in this paper that it is the main body of decision tree-like neural network based on probability theory. The minimum spanning tree mentioned in the graph theory of the algorithm view also has the matching property as the basis of the algorithm, and then introduces the application group theory base group representation theory to represent the node mapping properties between the trees.

　　After that, the time series is guided. Finally, the virtual algorithm should prove the infinite series and find the stability of the algorithm itself.

　　I hope to use the above case to understand the operation mode of artificial intelligence itself, and to optimize the basic program of this algorithm. Finally, in view of the quantum computer operation system, the quantum equations are also compared with the organic rate amplitude to summarize the new theorem.

Methodology / Approach

　　The research method is that the past mathematical theories are independent events and each has its own difficulties. This situation can be explained by the following three aspects: Firstly, the current fractal data is based on the plane system calculus, but it can be in the field of quantum mechanics. The superposition state is dominant, so if we can find the superposition state fractal calculation, we can deduct the artificial intelligence technology into quantum measurement.

　　The uncertainty theorem has a node error value. The last probability theory cannot be easily proved on the Lindenmeer system, so it is necessary to find the best solution of the relevant number. Therefore, we will first implement the computer science algorithm, and construct the basic environment to illustrate the basic properties of the discrete random variables. Then we will introduce the virtual algorithm between the probability theory and the decision tree by the previous research formula, by importing different nodes. The tree-generating nature illustrates the scope of application of this study.

Technologies Used

　　The research technique is to use artificial intelligence mathematical model to probability theory; Heisenberg uncertainty uncertainty theorem; and fractal theory as the basis of the initial research, and then introduce the isomorphic group and homomorphic group mentioned in the application group theory; The traversal search method of the spanning tree count followed by the graph theory of the viewpoint; the discrete stochastic variables of the probability structure, the measurement environment required by the virtual algorithm is set, and the set property of the set theory is explained, and then the related theorem is proved. Construct artificial intelligence itself to learn the standard of random variables such as random numbers; analyze the data categories; and mainly verify the theory of computer science algorithms.

Other links

• Decision tree neural network based on discrete random variables basic mathematical model virtual algorithm theorem