What is an autoencoder and what are the common variants?
mediumAnswer
- An autoencoder learns to compress input x through a bottleneck and reconstruct it.
- Variants: denoising AE (train to reconstruct clean from noisy input), sparse AE (bottleneck via sparsity penalty), variational AE (probabilistic latent, generative), masked AE (mask patches, reconstruct — used in vision pretraining).
- Uses: dimensionality reduction, denoising, anomaly detection, pretraining.
Check yourself — multiple choice
- Autoencoders are supervised classifiers
- A VAE has a probabilistic latent space and can generate samples
- Denoising autoencoders remove the bottleneck
- Autoencoders cannot be used for anomaly detection
VAEs impose a distribution on the latent code, enabling generation.
#representation-learning#deep-learning
Practise Unsupervised Learning
214 interview questions in this topic.