Backpropagation, intuitively | Deep Learning Chapter 3

延伸阅读 1

同一个手写数字会对许多权重提出大小不同的调整。前一层亮起的神经元不同，同样改一点权重，对输出的影响也不同。不同样本的建议还要合并。

作者英文字幕 ↗ · 引文按字幕原文展示，可点时间戳回看片段。

补充字幕原文 2

We can't directly change those activations, we only have influence on the weights and biases.

And zooming out a bit further, remember that this is all just how a single training example wishes to nudge each one of those weights and biases.