Deep Learning CNN Convolutional Neural Networks with Python - Rprop and Momentum Solution

The video tutorial explains an equation with two terms: the learning rate and momentum. The learning rate updates existing weights, while momentum considers previous weight changes to optimize current weights. This approach helps find optimal points in a convex or loss function.

What is the significance of considering the weights of the previous epoch?

In what way does momentum help in finding optimal points in a convex function?