We present a comprehensive study of the use of generative modeling approaches for Multiple-Instance Learning (MIL) problems. In MIL a learner receives training instances grouped together into bags with labels for the bags only (which might not be correct for the comprised instances). Our work was motivated by the task of facilitating the diagnosis of neuromuscular disorders using sets of motor ...

Generative adversarial networks (GANs) has gained tremendous popularity lately due to an ability to reinforce quality of its predictive model with generated objects and the quality of the generative model with and supervised feedback. GANs allow to synthesize images with a high degree of realism. However, the learning process of such models is a very complicated optimization problem and certain...

Developments in deep generative models have allowed for tractable learning of high-dimensional data distributions. While the employed learning procedures typically assume that training data is drawn i.i.d. from the distribution of interest, it may be desirable to model distinct distributions which are observed sequentially, such as when different classes are encountered over time. Although cond...

We propose an adversarial training procedure for learning a causal implicit generative model for a given causal graph. We show that adversarial training can be used to learn a generative model with true observational and interventional distributions if the generator architecture is consistent with the given causal graph. We consider the application of generating faces based on given binary labe...

Redox activity was measured in vegetative and generative apical parts (5 mm of the stem) and youngest leaves of winter (cv. "G6rczański") and spring (cv. "Młochowski") rape. Both genotypes were cultured under the same growth conditions (17/15 degrees C day/night, 16 h photo-period), but winter rape was additionally vernalized (5/2 degrees C day/night, 56 days) in order to induce the generative ...

For several decades, statisticians have advocated using a combination of labeled and unlabeled data to train classifiers by estimating parameters of a generative model through iterative Expectation-Maximization (EM) techniques. This chapter explores the effectiveness of this approach when applied to the domain of text classification. Text documents are represented here with a bag-of-words model...

Sensate environments provide a medium for humans to interact with space. This interaction includes ambient/passive triggering, performative artistic interaction and physical sensate spaces used for games and interactive entertainment. This paper examines aural representations of data activated by interaction, shaped by user activities and social environmental behaviours. Generative art forms, f...

Deep generative models (DGMs) are effective on learning multilayered representations of complex data and performing inference of input data by exploring the generative ability. However, it is relatively insufficient to empower the discriminative ability of DGMs on making accurate predictions. This paper presents max-margin deep generative models (mmDGMs) and a class-conditional variant (mmDCGMs...

Generative Adversarial Networks (GANs) have shown impressive performance in generating photo-realistic images. They fit generative models by minimizing certain distance measure between the real image distribution and the generated data distribution. Several distance measures have been used, such as Jensen-Shannon divergence, f -divergence, and Wasserstein distance, and choosing an appropriate d...

Generative adversarial networks have been proposed as a way of efficiently training deep generative neural networks. We propose a generative adversarial model that works on continuous sequential data, and apply it by training it on a collection of classical music. We conclude that it generates music that sounds better and better as the model is trained, report statistics on generated music, and...