Terence Parr personal blog
Explaining RNNs without neural networks
This article explains how recurrent neural networks (RNN's) work without using the neural network metaphor. It uses a visually-focused data-transformation perspective to show how RNNs encode variable-length input vectors as fixed-length embeddings. Included are PyTorch implementation notebooks that use just linear…
- Points
- 126
- HN comments
- 7
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningSoftware Engineering2020
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Jul 10, 2020 | Explaining RNNs without neural networks by parrt | 126 | 7 |
