Backpropagation - Wikipedia
7
Public whispers
6
Contributors
2026-06-18 09:09:18
First whispered
Public whispers on this page
Text Highlight2026-07-26 16:05:42
Original Highlight Excerpt
"Strictly speaking, the term backpropagation refers only to an algorithm for efficiently computing the gradient, not how the gradient is used"
Whisper Note
So it's just the gradient part, like a tool, not the whole learning thing.
Text Highlight2026-07-26 13:02:42
Original Highlight Excerpt
"efficient application of the chain rule to neural networks"
Whisper Note
So many tutorials skip the 'efficient' part and just drown you in math.
Text Highlight2026-07-26 12:53:42
Original Highlight Excerpt
"efficient application of the chain rule to neural networks"
Whisper Note
Wait, isn't that just the chain rule with extra steps?
Text Highlight2026-07-26 09:59:42
Original Highlight Excerpt
"backpropagation is a gradient computation method commonly used for training a neural network"
Whisper Note
basically the chain rule on steroids, right?
Text Highlight2026-07-26 09:50:42
Original Highlight Excerpt
"backpropagation is a gradient computation method commonly used for training a neural network"
Whisper Note
i always mix this up with the optimizer, makes sense now
Text Highlight2026-07-26 09:41:42
Original Highlight Excerpt
"backpropagation is a gradient computation method commonly used for training a neural network"
Whisper Note
so it's just gradients, not the whole algorithm, huh
Text Highlight2026-06-18 09:09:18
Original Highlight Excerpt
"the term is often used loosely to refer to the entire learning algorithm"
Whisper Note
Good point, most people mean the whole training loop when they say backprop.
Share this page's whispers
Short link
https://domwhisper.com/s/3b380be231deEmbed snippet
<iframe src="https://domwhisper.com/embed/3b380be231de" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>See what people are discussing on en.wikipedia.org
Install DomWhisper to view live whispers as you browse, and join the discussion.
Get the extension