What is an Auto-Encoder?
Autoencoders are structured to take an input, transform this input into a different representation, an embedding of the input. From this embedding, it aims to reconstruct the original input as precisely as possible. It basically tries to copy the input.
https://medium.com/@jannik.zuern/but-what-is-an-autoencoder-26ec3386a2af#:~:text=Autoencoders%20are%20structured%20to%20take,tries%20to%20copy%20the%20input.
https://medium.com/swlh/introduction-to-autoencoders-56e5d60dad7f
Autoencoders are obtained from unsupervised deep learning algorithm.
We train a deep neural network with a bottleneck, where we keep the input and output identical.
Autoencoders are used for the lower dimensional representation of input features.
Autoencoders are used in following cases -
- To reduce the dimension of linear and non-linear data. That is the primary reason of its superiority over PCA.
- It is also used in recommendation systems, they are good at understanding user preferences.
- They are used to extract important features.
- Multiple features of an image can be understood by using multiple autoencoders.