"Machine Learning"의 두 판 사이의 차이
ph
잔글 (→general) |
잔글 (→general) |
||
| 26번째 줄: | 26번째 줄: | ||
** [[highway networks]] | ** [[highway networks]] | ||
** [[densely connected convolutional networks|DenseNet]] | ** [[densely connected convolutional networks|DenseNet]] | ||
| + | ** [[Network in Network|NIN]] | ||
| + | ** [[Deeply Supervised Network|DSN]] | ||
| + | ** [[Ladder Networks]] | ||
| + | ** [[Deeply-Fused Nets|DFNs]] | ||
* [[Learning to learn by GD by GD]] | * [[Learning to learn by GD by GD]] | ||
* [[Generative Models]] | * [[Generative Models]] | ||
2017년 7월 24일 (월) 12:17 판
by themes
ril
- https://medium.com/technologymadeeasy/the-best-explanation-of-convolutional-neural-networks-on-the-internet-fbb8b1ad5df8
- http://nmhkahn.github.io/Casestudy-CNN
- https://stats.stackexchange.com/questions/205150/how-do-bottleneck-architectures-work-in-neural-networks
- https://www.quora.com/What-exactly-is-the-degradation-problem-that-Deep-Residual-Networks-try-to-alleviate
- dl with torch
- bias 붙여버리면 inv는 어케 구하나? D=0되지 않나? 구할필요 없나?
- pytorch examples
- Identity Mappings in Deep Residual Networks arXiv:1603.05027