티스토리 뷰
AutoEncoder
- A way for unsupervised learning for nonlinear manifold
- ANN used for unsupervised learning of efficient codings
- Aim : To learn a representation for set of data
- Purpose : Dimensionality reduction
[Keyword]
◾ Unsupervised learning
◾ Manifold learning
= Nonlinear Dimensionality reduction
= Representation learning
= Efficient coding learning
= Feature extraction
◾ Generative model learning
◾ ML density estimation
AutoEncoder를 학습할 때
- 학습방법은 Unsupervised learning
- Loss는 negative ML (ML density estimation)
ML : Maximum Likelihood
학습된 AutoEncoder 에서
- Encoder는 차원 축소 (Manifold learning)
- Decoder는 생성 모델 (Generative model)
'DL > AutoEncoder' 카테고리의 다른 글
[Ch5] Applications (Retrieval, Generation, GAN+VAE) (0) | 2022.02.22 |
---|---|
[Ch4] Variational AutoEncoders (VAE, CVAE, AAE) (0) | 2022.01.31 |
[Ch3] AutoEncoders (AE, DAE, CAE) (0) | 2022.01.30 |
[Ch2] Manifold Learning (0) | 2022.01.30 |
[Ch1] Revisit Deep Neural Networks (0) | 2022.01.30 |
댓글
공지사항