AI & MLRecommendedAIML-GM-002
Autoencoders
Compress then reconstruct: a learned bottleneck, and why a plain autoencoder is not yet a generative model.
- Difficulty
- 3 / 5
- Importance
- 4 / 5
- Study time
- 1–2 h
- Kind of work
- Mixed
Why it matters
The learner can vary bottleneck width and explain the reconstruction trade-off and why decoding random codes gives poor samples.