The trailing gradient problem is encountered when training artificial neural networks with learning methods based on gradient and backpropagation.
In such methods, during each learning iteration, each of the weights of the neural network receives an update proportional to the partial derivative of the error function with respect to the current weight.
In some cases, the gradient will be very small, preventing the weight from changing value.
Which can prevent the neural network from continuing to train.
Welcome, my name is Eric Soupet and I am the administrator of the site elodees.com. elodees.com is a state of the art of Artificial Intelligence and aims to be collaborative, you can now offer content such as articles, events, tutorials, ... so don't hesitate !
