误差就是要优化的对象，神经网络被设定为让误差最小。举一个例子：例如给出

The error is the object to be optimized, and the neural network is set to minimize the error. Take an example: For example, give a bunch of independent variables x1, x2, x3, x4, and a dependent variable y1. In the training set. One set of data is [2,4,6,7] and 12. The output of the neural network is 11. Then the error is 11-12 = -1. The error is "actual output-network output". The objective function should minimize the error to achieve accurate prediction.

Error is the object that is optimized, and the neural network is set to minimize the error. As an example: give a bunch of arguments x1, x2, x3, x4, a dependent variable y1. In the training set. There is a set of data that is 2, 4, 6, 7, and 12. The neural network output is 11. Then the error is 11-12-1. The error is "actual output - network output". The objective function should minimize the error for the purpose of accurate prediction.

The error is the object to be optimized, and the neural network is set to minimize the error. Take an example: for example, give a bunch of independent variables x1, X2, X3, x4, and a dependent variable Y1. In the training center. One set of data is [2,4,6,7] and 12. The output of neural network is 11. Then the error is 11-12 = - 1. Error is "actual output network output". The objective function should minimize the error to achieve the goal of accurate prediction.<br>