这是神经网络的中心内容。首先，记住这句话：梯度方向是下降速度最快的方向

This is the central content of the neural network. First of all, remember this sentence: the gradient direction is the direction of the fastest descent, don't ask why, just remember. Therefore, when the neural network adjusts the weight according to the error, it is adjusted according to the direction of gradient descent. <br>Secondly, the essence of back propagation is the back propagation of error information. Because only through the back propagation of error information, the previous neurons can know how to adjust their own weights and thresholds to optimize the network. Backpropagation should also distribute error information according to weights. Neurons with large weights have a large adjustment range, while neurons with small weights have a small adjustment range. After all, those with large weights should bear the main responsibility.

The present is a good time to present the present. ...

This is the central content of neural network. First of all, remember this sentence: gradient direction is the direction of the fastest descent speed. Don't ask why, just remember it. Therefore, when the neural network adjusts the weight according to the error, it adjusts according to the direction of gradient descent.<br>Secondly, the essence of back propagation is the back propagation of error information. Because only through the back propagation of error information, the front neurons can know how to adjust their weights and thresholds to optimize the network. Back propagation should also allocate error information according to the weight. The neuron with large weight has a large adjustment range, while the neuron with small weight has a small adjustment range. After all, the neuron with large weight should bear the main responsibility.