Výsledky vyhledávání - "Paulo E. Rauber"

Reinforcement Learning in Sparse-Reward Environments With Hindsight Policy Gradients

Autor: Filipe Mutz, Paulo E. Rauber, Jürgen Schmidhuber, Avinash Ummadisingu

Publikováno v: Neural Computation. 33:1498-1553

A reinforcement learning agent that needs to pursue different goals across episodes requires a goal-conditional policy. In addition to their potential to generalize desirable behavior to unseen goals, such policies may also enable higher-level planni

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ffde3a641ec00e6ca2c4913c7ff73619
https://doi.org/10.1162/neco_a_01387

Zobrazit plný text záznamu

Projections as visual aids for classification system design

Autor: Alexandre X. Falcão, Paulo E. Rauber, Alexandru Telea

Publikováno v: Information visualization, 17(4), 282-305. SAGE Publications Inc.

Dimensionality reduction is a compelling alternative for high-dimensional data visualization. This method provides insight into high-dimensional feature spaces by mapping relationships between observations (high-dimensional vectors) to low (two or th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9f3b36c253199d570acd416a236e8dbd
https://hdl.handle.net/11370/07b8fe62-4ef8-41e0-a4a5-7d3a810b64c5

Zobrazit plný text záznamu

Beyond the Third Dimension

Autor: Renato Ramos da Silva, Alexandru Telea, Paulo E. Rauber

Publikováno v: Computing in Science & Engineering, 18(5), 98-107. IEEE Computer Society

Multidimensional projections are an increasingly popular technique for visualizing large datasets containing observations having tens or even hundreds of dimensions. Compared to other techniques such as parallel coordinates, tables, and scatterplot m

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::16d3a0bf85a308d156e6def212c98daf
https://hdl.handle.net/11370/71cf8aaf-e053-4c97-86d1-f54f0838f3f9

Zobrazit plný text záznamu

Visualizing the Hidden Activity of Artificial Neural Networks

Autor: Alexandru Telea, Samuel G. Fadel, Paulo E. Rauber, Alexandre X. Falcão

Publikováno v: IEEE Transactions on Visualization and Computer Graphics, 23(1), 101-110. IEEE COMPUTER SOC

In machine learning, pattern classification assigns high-dimensional vectors (observations) to classes based on generalization from examples. Artificial neural networks currently achieve state-of-the-art results in this task. Although such networks a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e99db2e87f05489f2d727185a636c6b3
https://pubmed.ncbi.nlm.nih.gov/27875137

Zobrazit plný text záznamu

Effcient and Effective Automated Digital Hair Removal from Dermoscopy Images

Autor: Joost Koehoorn, André Sobiecki, Paulo E. Rauber, Alexandru Telea, Andrei C. Jalba

Publikováno v: Mathematical Morphology, 1(1), 1-17. De Gruyter Open Ltd.

We propose a method for digital hair removal from dermoscopic images, based on a threshold-set model. For every threshold, we adapt a recent gap-detection algorithm to find hairs, and merge results in a single mask image.We find hairs in this mask by

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a8396b4255e16fe386ee4589ae4f890f
https://doi.org/10.1515/mathm-2016-0001

Zobrazit plný text záznamu

Interactive Segmentation by Image Foresting Transform on Superpixel Graphs

Autor: Paulo E. Rauber, Thiago Vallin Spina, Pedro J. de Rezende, Alexandre X. Falcão

Publikováno v: SIBGRAPI

There are many scenarios in which user interaction is essential for effective image segmentation. In this paper, we present a new interactive segmentation method based on the Image Foresting Transform (IFT). The method over segments the input image,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::342f89f59fa50b68c94356a07c08234d
https://doi.org/10.1109/sibgrapi.2013.27

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání