Models & inference · Glossary term
What is VAE (Variational Autoencoder)?
A latent-variable model trained with a reconstruction objective and a regularization term that keeps an approximate posterior close to a chosen prior. The reparameterization estimator allows gradients through stochastic latent sampling.
“A probabilistic generative autoencoder.”
What is the common confusion about VAE (Variational Autoencoder)?
A VAE does not force every latent distribution to one fixed Gaussian; the exact prior and approximate posterior are modeling choices.
Learn VAE (Variational Autoencoder) in the course
Lessons that name VAE (Variational Autoencoder) in a title or section
- Autoencoders & Variational Autoencoders (VAE)
A plain autoencoder compresses then reconstructs. It memorizes. It does not generate. Add one trick — force the code to look Gaussian — and you get a sampler.
- Sampling Methods
Sampling is how AI explores the space of possibilities. Language: Python Implement inverse CDF, rejection, and importance sampling from scratch using only uniform random numbers.
Covered in Phase 01: Math Foundations and Phase 08: Generative AI.
Related terms
- Latent SpaceA learned representation space whose coordinates encode factors useful to a model. It may be lower-dimensional than the input, but…
- EncoderA component that transforms input into a representation. A transformer encoder commonly uses non-causal self-attention, subject to any…
- DecoderA component that maps a representation into an output. In an encoder-decoder transformer, the decoder uses masked self-attention and…
- Diffusion ModelA generative model trained around a progressive noising process and a learned reverse process.
- Image TokenA model-specific visual unit represented as a vector or discrete code, commonly derived from an image patch, region, or learned…
Sources
More terms in Models & inference
- Attention
- Autoregressive
- CNN (Convolutional Neural Network)
- CUDA
- Decoder
- Decoding Strategy
- Diffusion Model
- Encoder
- GAN (Generative Adversarial Network)
- GPT
- Inductive Bias
- Inference
- KV Cache
- LLM (Large Language Model)
- Logits
- MoE (Mixture of Experts)
- Nucleus Sampling (Top-p)
- Parameter
- Perplexity
- Quantization
- Self-Attention
- Speculative Decoding
- Stop Sequence
- Streaming
- Temperature
- Time to First Token (TTFT)
- Top-k Sampling
- Transformer
This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.