非凸性：一个系统的演化方向，在一定条件下将取决于某个特定的状态函数。例

Non-convexity: The evolution direction of a system will depend on a certain state function under certain conditions. For example, the energy function, its extreme value corresponds to the relatively stable state of the system. Non-convexity means that this function has multiple extreme values, so the system has multiple stable equilibrium states, which will lead to the diversity of system evolution. <br>The artificial neural network model mainly considers the topological structure of the network connection, the characteristics of the neurons, and the learning rules. At present, there are nearly 40 neural network models, including backpropagation networks, perceptrons, self-organizing maps, Hopfield networks, Boltzmann machines, adaptive resonance theory, etc. According to the connected topology, the neural network model can be divided into

Non-convex: The evolutionary direction of a system, under certain conditions, will depend on a particular state function. For example, the energy function, whose extremum corresponds to the relatively stable state of the system. Non-convexmeaning means that this function has multiple extremums, so the system has multiple stable equilibrium states, which will lead to the diversity of system evolution.<br>The artificial neural network model mainly considers the topology of network connection, the characteristics of neurons, learning rules and so on. At present, there are nearly 40 neural network models, including back-transmission network, perceptible, self-organizing mapping, Hopfield network, Borzman machine, adaptive resonance theory and so on. According to the topology of the connection, the neural network model can be divided into.

Nonconvexity: the evolution direction of a system depends on a specific state function under certain conditions. For example, the extreme value of the energy function corresponds to the relatively stable state of the system. Non convexity means that the function has multiple extremum, so the system has many stable equilibrium states, which will lead to the diversity of system evolution.<br>The artificial neural network model mainly considers the topological structure of network connections, the characteristics of neurons and learning rules. At present, there are nearly 40 kinds of neural network models, including back propagation network, perceptron, self-organizing map, Hopfield network, Boltzmann machine, adaptive resonance theory and so on. According to the topological structure of the connection, the neural network model can be divided into