Generative Adversarial Networks (GAN) have become one of the most studied frameworks for unsupervised learning due to their intuitive formulation. They have also been shown to be capable of generating convincing examples in limited domains, such as low-resolution images. However, they still prove difficult to train in practice and tend to ignore modes of the data generating distribution. Quanti...

Discriminative learning, or learning for classification, is a common learning task that has been addressed in a variety of frameworks. One approach is to design a complex classifier, such as a support vector machine, that explicitly minimizes classification error. Alternatively, an ensemble of weak classifiers can be trained using boosting [4]. However, in some situations it may be desirable to...

In this paper, we propose a generative model which learns the relationship between language and human action in order to generate a human action sequence given a sentence describing human behavior. The proposed generative model is a generative adversarial network (GAN), which is based on the sequence to sequence (SEQ2SEQ) model. Using the proposed generative network, we can synthesize various a...

In this paper, we evaluate a generative-discriminative approach for multi-modal tumor segmentation that builds – in its generative part – on a generative statistical model for tumor appearance in multi-dimensional images [1] by using a “latent” tumor class [2, 3], and – in its discriminative part – on a machine learning approach based on a random forest using long-range features that is capable...

Classical approaches to classifier learning for structured objects (such as images or sequences) are based on probabilistic generative models. On the other hand, state-of-the-art classifiers for vectorial data are learned discriminatively. In recent years, these two dual paradigms have been combined via the use of generative embeddings (of which the Fisher kernel is arguably the best known exam...

A construction tree is a set of shape generation processes commonly produced with CAD modelers during a design process of B-Rep objects. However, a construction tree does not bring all the desired properties in many configurations: dimension modifications, idealization processes,. . . Generating a non trivial set of generative processes, possibly forming a construction graph, can significantly ...

The evolution of life on earth has been characterized by generalized long-term increases in phenotypic complexity. Although natural selection is a plausible cause for these trends, one alternative hypothesis--generative bias--has been proposed repeatedly based on theoretical considerations. Here, we introduce a computational model of a developmental system and use it to test the hypothesis that...

Models of autobiographical memory propose two routes to retrieval depending on cue specificity. When available cues are specific and personally-relevant, a memory can be directly accessed. However, when available cues are generic, one must engage a generative retrieval process to produce more specific cues to successfully access a relevant memory. The current study sought to characterize the ne...

References: [1] Celestino Soddu, “Milan Identity”, Gangemi Pub, 2005 [2] C. Soddu, E.Colabella, “Il Progetto Ambientale di Morfogenesi”, Leonardo project, 1992 [3] www.generativeart.com www.soddu.it Abstract: looking at a sequence of artworks we can immediately identify which artist made it. But only if the artist imprinting, the artist style and unicity exists. Make own arworks recognizable as...

Most approaches to classifier learning for structured objects (such as images or sequences) are based on probabilistic generative models. On the other hand, state-of-the-art classifiers for vectorial data are learned discriminatively. In recent years, these two dual paradigms have been combined via the use of generative embeddings (of which the Fisher kernel is arguably the best known example);...