Watch and track your favorite playlist.
Curated by: UvA Deep Learning course (34 videos)
In this tutorial, we implement an autoregressive likelihood model for the task of image modeling. Autoregressive models are naturally strong generative models that constitute one of the current state-of-the-art architectures on likelihood-based image modeling, and are also the basis for large language generation models such as GPT3. We will focus on the PixelCNN architecture in this tutorial, and apply it to MNIST modeling. This notebook is part of a lecture series on Deep Learning at the University of Amsterdam. The full list of tutorials can be found at https://uvadlc-notebooks.rtfd.io. Link to the notebook: https://uvadlc-notebooks.readthedocs.io/en/latest/tutorial_notebooks/tutorial12/Autoregressive_Image_Modeling.html 00:00 Intro 03:39 Masked Autoregressive Convolutions 05:57 Vertical and Horizontal Stack Convolutions 08:04 Visualizing the receptive field