For more than a century, the methods for data representation and the exploration of the
intrinsic structures of data have developed remarkably and consist of supervised and …

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 …

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 …

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 …