Generative learning
Found 3 free book(s)Introduction to Deep Learning - Stanford University
graphics.stanford.eduWhat is Deep Learning? Deep learning allows computational models that are composed of multiple processing layers to learn ... Discarding pooling layers has been found to be important in training good generative models, such as variational autoencoders (VAEs) or generative adversarial networks (GANs).
A fast learning algorithm for deep belief nets
www.cs.toronto.edu2. The learning algorithm is unsupervised but can be ap-plied to labeled data by learning a model that generates both the label and the data. 3. There is a fine-tuning algorithm that learns an excel-lent generative model which outperforms discrimina-tive methods on the MNIST database of hand-written digits. 4.
Graph Representation Learning - McGill University School ...
www.cs.mcgill.cavestigating deep learning methods for \embedding" graph-structured data. In the years since 2013, the eld of graph representation learning has witnessed a truly impressive rise and expansion|from the development of the standard graph neural network paradigm to the nascent work on deep generative mod-els of graph-structured data.