Autoencoder is an unsupervised artificial neural network that learns how to efficiently compress and encode data then learns how to reconstruct the data back from the reduced encoded representation to a representation that is as close to the original input as possible.
Autoencoder, by design, reduces data dimensions by learning how to ignore the noise in the data.
Auto EncoderDenoising Auto EncoderSparse Auto EncoderVariational Auto EncoderGenerative Adversarial Network
- https://medium.com/machine-learning-researcher/auto-encoder-d942a29c9807
- https://towardsdatascience.com/auto-encoder-what-is-it-and-what-is-it-used-for-part-1-3e5c6f017726 (unlock with incognito)
- https://www.jeremyjordan.me/autoencoders/
- https://www.mygreatlearning.com/blog/autoencoder/
- https://blog.keras.io/building-autoencoders-in-keras.html
- https://www.youtube.com/watch?v=yFBFl1cLYx8
- https://medium.com/analytics-vidhya/what-is-auto-encoder-in-deep-learning-5d668f94651b
- https://debuggercafe.com/autoencoders-in-deep-learning/
- https://www.datacamp.com/community/tutorials/autoencoder-keras-tutorial