Christopher Olah personal blog
Calculus on Computational Graphs: Backpropagation (2015)
Backpropagation is the key algorithm that makes training deep models computationally tractable. For modern neural networks, it can make training with gradient descent as much as ten million times faster, relative to a naive implementation. That’s the difference between a model taking a week to train and taking 200,000…
- Points
- 170
- HN comments
- 33
- Submissions
- 2
- Cited by
- 4 commenters
AI & Machine LearningMath & Algorithms2024
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Jan 19, 2024 | Calculus on Computational Graphs: Backpropagation (2015) by throwup238 | 170 | 24 |
| Aug 31, 2015 | Calculus on Computational Graphs: Backpropagation by inetsee | 55 | 9 |
Cited in comments
Linked from 4 Hacker News comments by 4 different people, from Jan 2016 to Oct 2021.
Most recent:
- minihat · Oct 11, 2021
- paraschopra · Oct 23, 2018
- attractivechaos · Apr 10, 2018
- pjscott · Jan 9, 2016
