DP Kingma, S Mohamed… - Advances in neural …, 2014 - proceedings.neurips.cc
The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical …
Discovering what is learned by neural networks remains a challenge. In self-supervised learning, classification is the most common task used to evaluate how good a representation …
Normalizing flows transform a latent distribution through an invertible neural network for a flexible and pleasingly simple approach to generative modelling, while preserving an exact …
GJ Qi, J Luo - IEEE Transactions on Pattern Analysis and …, 2020 - ieeexplore.ieee.org
Representation learning with small labeled data have emerged in many problems, since the success of deep neural networks often relies on the availability of a huge amount of labeled …
Z Zhang, R Zhang, Z Li, Y Bengio… - … on Machine Learning, 2020 - proceedings.mlr.press
Modern generative models are usually designed to match target distributions directly in the data space, where the intrinsic dimension of data can be much lower than the ambient …
Generative models can be used for a wide range of tasks, and have the appealing ability to learn from both labelled and unlabelled data. In contrast, discriminative models cannot learn …
The ability of the Generative Adversarial Networks (GANs) framework to learn generative models mapping from simple latent distributions to arbitrarily complex data distributions has …
Synthetic data consists of artificially generated data. When data are scarce, or of poor quality, synthetic data can be used, for example, to improve the performance of machine …
Generative models have been in existence for many decades. In the field of machine learning, we come across many scenarios when directly learning a target is intractable …