An autoencoder is a Neural network that tries to reconstruct its own input through a bottleneck. It’s a dimensionality reduction technique.
Since it doesn’t require labeling, it’s an unsupervised machine learning method.
A linear autoencoder (an autoencoder without activation functions) is roughly equivalent to a PCA.
@article{yaltirakli, title = "Autoencoder", author = "Yaltirakli, Gokberk", journal = "gkbrk.com", year = "2024", url = "https://www.gkbrk.com/autoencoder" }
Gokberk Yaltirakli, "Autoencoder", July, 2024. [Online]. Available: https://www.gkbrk.com/autoencoder. [Accessed Jul. 24, 2024].
Yaltirakli, G. (2024, July 24). Autoencoder. https://www.gkbrk.com/autoencoder
Gokberk Yaltirakli, Autoencoder, GKBRK.COM (Jul. 24, 2024), https://www.gkbrk.com/autoencoder
