It abstracts the neural network of human brain from the perspective of information processing, establishes a simple model, and forms different networks according to different connection methods. In engineering and academic circles, it is usually called neural network for short or directly. Neural network is an operational model, which consists of a large number of interconnected nodes (or neurons). Each node represents a specific output function, which is called an excitation function.
The connection between every two nodes represents a weighted value of the signal passing through the connection, which is called weight, which is equivalent to the memory of artificial neural network. The output of the network varies according to the connection mode, weight and excitation function of the network. The network itself is usually an approximation of some algorithm or function, or it may be an expression of a logical strategy.
In recent ten years, the research work of artificial neural network has been deepened and made great progress. It has successfully solved many practical problems that are difficult to be solved by modern computers in the fields of pattern recognition, intelligent robots, automatic control, prediction and estimation, biology, medicine and economy, and has shown good intelligent characteristics.
The characteristics and advantages of artificial neural network are mainly manifested in three aspects:
1, with self-learning function. For example, when realizing image recognition, it is only necessary to input many different image templates and corresponding results to be recognized into the artificial neural network, and the network will gradually learn to recognize similar images through the self-learning function. Self-learning function is of great significance to prediction. It is predicted that the artificial neural network computer in the future will provide economic forecast, market forecast and benefit forecast for human beings, and its application prospect is very broad.
2, with associative storage function. This correlation can be realized by using the feedback network of artificial neural network.
3. Have the ability to find the optimal solution at high speed. Finding the optimal solution of a complex problem often requires a lot of calculation. Using the feedback artificial neural network designed for a problem and giving full play to the high-speed computing ability of the computer, the optimal solution may be found soon.