Search results for "Generative Grammar"
showing 10 items of 33 documents
Marked systems and circular splicing
2007
Splicing systems are generative devices of formal languages, introduced by Head in 1987 to model biological phenomena on linear and circular DNA molecules. In this paper we introduce a special class of finite circular splicing systems named marked systems. We prove that a marked system S generates a regular circular language if and only if S satisfies a special (decidable) property. As a consequence, we show that we can decide whether a regular circular language is generated by a marked system and we characterize the structure of these regular circular languages.
POSSIBILITY OF THE USAGE OF THE VISUAL RESEARCH METHODS WITHIN THE DESIGN EDUCATION
2017
Young people are forming and will form the environment of today and tomorrow. This reinforces the necessity of the young generation’s active involvement in the promotion of positive change. This approach cannot be otherwise as systemic and impossible without research and data analysis. Visual research methods, which are self-evident in design and art, are widely used in a number of other disciplines. To achieve an objective and reliable results, they often are combined with quantitative, analytic, generative and other methods. The aim of the paper - to discuss the ways of visual research methods' use in combination with systemic design thinking approach in finding new solutions in promotion…
Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis
2016
This paper studies a combination of generative Markov random field (MRF) models and discriminatively trained deep convolutional neural networks (dCNNs) for synthesizing 2D images. The generative MRF acts on higher-levels of a dCNN feature pyramid, controling the image layout at an abstract level. We apply the method to both photographic and non-photo-realistic (artwork) synthesis tasks. The MRF regularizer prevents over-excitation artifacts and reduces implausible feature mixtures common to previous dCNN inversion approaches, permitting synthezing photographic content with increased visual plausibility. Unlike standard MRF-based texture synthesis, the combined system can both match and adap…
The intentional stance as structure learning: a computational perspective on mindreading
2015
Recent theories of mindreading explain the recognition of action, intention, and belief of other agents in terms of generative architectures that model the causal relations between observables (e.g., observed movements) and their hidden causes (e.g., action goals and beliefs). Two kinds of probabilistic generative schemes have been proposed in cognitive science and robotics that link to a "theory theory" and "simulation theory" of mindreading, respectively. The former compares perceived actions to optimal plans derived from rationality principles and conceptual theories of others' minds. The latter reuses one's own internal (inverse and forward) models for action execution to perform a look…
Supporting fine-grained generative model-driven evolution
2010
Published version of an article in the journal: Software and Systems Modeling. Also available on SpringerLink:http://dx.doi.org/10.1007/s10270-009-0144-1 In the standard generative Model-driven Architecture (MDA), adapting the models of an existing system requires re-generation and restarting of that system. This is due to a strong separation between the modeling environment and the runtime environment. Certain current approaches remove this separation, allowing a system to be changed smoothly when the model changes. These approaches are, however, based on interpretation of modeling information rather than on generation, as in MDA. This paper describes an architecture that supports fine-gra…
Domain Adaptation of Landsat-8 and Proba-V Data Using Generative Adversarial Networks for Cloud Detection
2019
Training machine learning algorithms for new satellites requires collecting new data. This is a critical drawback for most remote sensing applications and specially for cloud detection. A sensible strategy to mitigate this problem is to exploit available data from a similar sensor, which involves transforming this data to resemble the new sensor data. However, even taking into account the technical characteristics of both sensors to transform the images, statistical differences between data distributions still remain. This results in a poor performance of the methods trained on one sensor and applied to the new one. In this this work, we propose to use the generative adversarial networks (G…
Categorization in Discourse and Grammar
2016
This collection of papers addresses new trends in Cognitive Linguistics. Three parts of the book focus on Conceptual Metaphor Theory and Integration Network Analysis. Both the theoretical contributions and the empirical case studies stress the importance of contextual factors in the meaning making processes. They employ qualitative methods to analyze the use of metaphor in political discourse and in the conceptualization of emotions. The data sets include multimodal data, sign languages and co-speech gestures. The fourth part of the book contains two corpus-based studies. The fifth part concentrates on the grammatical categories of passive voice and aspect. One contribution discusses the pr…
Kone ja automaatti
2011
Literary Machines and Automata: Feedbacking Poetics The article discusses the concepts of “machine”, “automatic”, and “feedback loop” as literary and poetic ideas from the terminological, historical, and contemporary perspectives. All of them can be seen as somewhat paradoxical terms, carrying human and organic connotations with them. The key phenomenon of this article is the generator, a machine or system that produces – generates – text. The history of poetic automata extends well beyond the Internet, computer, or even electricity. The article illustrates its claims with examples of poetry generators, from a combinatory poem of the Baroque era to a few Finnish contemporary digital works. …
Generating Hyperspectral Skin Cancer Imagery using Generative Adversarial Neural Network
2020
In this study we develop a proof of concept of using generative adversarial neural networks in hyperspectral skin cancer imagery production. Generative adversarial neural network is a neural network, where two neural networks compete. The generator tries to produce data that is similar to the measured data, and the discriminator tries to correctly classify the data as fake or real. This is a reinforcement learning model, where both models get reinforcement based on their performance. In the training of the discriminator we use data measured from skin cancer patients. The aim for the study is to develop a generator for augmenting hyperspectral skin cancer imagery. peerReviewed
The Dreaming Variational Autoencoder for Reinforcement Learning Environments
2018
Reinforcement learning has shown great potential in generalizing over raw sensory data using only a single neural network for value optimization. There are several challenges in the current state-of-the-art reinforcement learning algorithms that prevent them from converging towards the global optima. It is likely that the solution to these problems lies in short- and long-term planning, exploration and memory management for reinforcement learning algorithms. Games are often used to benchmark reinforcement learning algorithms as they provide a flexible, reproducible, and easy to control environment. Regardless, few games feature a state-space where results in exploration, memory, and plannin…