• Used to describe certain time-varying processes. Specifies that the output variable depends linearly on its own previous values and on a stochastic term (an imperfectly predictable term). -Wikipedia; Given examples from a distribution, generate samples belonging to the same distribution. -CSE598

Is a:

• method

Applications:

• Feature Extraction
• Image Generation

Advantages:

• can explicitly estimate likelihood p(x)
• pretty good results for generation
• simple and stable training process

Disadvantages:

• cannot provide low-dimensional latent space
• inefficient at generation because it is a sequential process, which cannot be parallelized