Atom Interface is a novel interactive visualization of single/multiple tree structures. It is based on the metaphor of electrons, atoms and molecules. For mo...
Based on the work of Apache CouchDB, PouchDB provides a simple API in which to store and retrieve JSON objects, due to the similiar API, and CouchDB’s HTTP API it is possible to sync data that is stored in your local PouchDB to an online CouchDB as well as syncing data from CouchDB down to PouchDB (you can even sync between 2 PouchDB databases).
RDF data can be analyzed with various query languages such as SPARQL
or SeRQL. Due to their nature these query languages do not support fuzzy queries.
In this paper we present a new method that transforms the information presented
by subject-relation-object relations within RDF data into Activation Patterns. These
patterns represent a common model that is the basis for a number of sophisticated
analysis methods such as semantic relation analysis, semantic search queries, unsuper-
vised clustering, supervised learning or anomaly detection. In this paper, we explain
the Activation Patterns concept and apply it to an RDF representation of the well
known CIA World Factbook.
This project adds a graphical user interface(GUI) for exporting data of Google Refine projects in RDF format. The export is based on mapping the data to a template graph using the GUI.
is a European project funded by the EU as part of the Seventh Research Framework Programme. The full project title is "Meeting the challenges of the farm of tomorrow by integrating Farm Management Information Systems to support real-time management decisions and compliance to standards", and the funding is under the Cooperation programme of the FP7 in the Food, Agriculture, Fisheries and Biotechnologies (Knowledge Based Bio-Economy) theme.
EU flag
Elefant (Efficient Learning, Large-scale Inference, and Optimisation Toolkit) is an open source library for machine learning licensed under the Mozilla Public License (MPL). We develop an open source machine learning toolkit which provides
algorithms for machine learning utilising the power of multi-core/multi-threaded processors/operating systems (Linux, WIndows, Mac OS X),
a graphical user interface for users who want to quickly prototype machine learning experiments,
tutorials to support learning about Statistical Machine Learning (Statistical Machine Learning at The Australian National University), and
detailed and precise documentation for each of the above.
The workshop aims to discuss key issues and practices of semantic mining. Thanks to the initiatives of the Linked Open Data and robust techniques for semantic annotation of Web, social, and sensor data, more semantic data is available. Many research efforts have been directed toward demonstrating semantic techniques to analyze and mine this growing resource. The workshop will provide a cross-disciplinary forum for researchers to showcase their innovation and efforts, and to further enhance existing bounds and create new connections among different communities. Here we solicit contributions on researches and practices of mining data semantics including theory, algorithms, and applications from computer science, life science, healthcare and other domains.
A great deal of research has focused on algorithms for learning features from un- labeled data. Indeed, much progress has been made on benchmark datasets like NORB and CIFAR by employing increasingly complex unsupervised learning al- gorithms and deep models. In this paper, however, we show that several very sim- ple factors, such as the number of hidden nodes in the model, may be as important to achieving high performance as the choice of learning algorithm or the depth of the model. Specifically, we will apply several off-the-shelf feature learning al- gorithms (sparse auto-encoders, sparse RBMs and K-means clustering, Gaussian mixtures) to NORB and CIFAR datasets using only single-layer networks. We then present a detailed analysis of the effect of changes in the model setup: the receptive field size, number of hidden nodes (features), the step-size (“stride”) be- tween extracted features, and the effect of whitening. Our results show that large numbers of hidden nodes and dense feature extraction are as critical to achieving high performance as the choice of algorithm itself—so critical, in fact, that when these parameters are pushed to their limits, we are able to achieve state-of-the- art performance on both CIFAR and NORB using only a single layer of features. More surprisingly, our best performance is based on K-means clustering, which is extremely fast, has no hyper-parameters to tune beyond the model structure it- self, and is very easy implement. Despite the simplicity of our system, we achieve performance beyond all previously published results on the CIFAR-10 and NORB datasets (79.6% and 97.0% accuracy respectively).
HEigen is a spectral analysis tool which computes top k eigenvalues and corresponding eigenvectors of extremely large(~billions of nodes and edges) graphs. HEigen runs on top of Hadoop platform.
A pre-relational databases datamodel. "Preceeded" by the relational model since the flexibility of this makes it hard to work with. Now re-invented in RDF :)
Die gezeigten Posts sind eventuell nicht akkurat bei Änderungen, die vor Kurzem vorgenommen worden. Wollen Sie jedoch akkurate Posts mit eingeschränkten Sortierungsmöglichkeiten, folgen Sie dem folgenden Link.
D. Shahaf, C. Guestrin, und E. Horvitz. Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining, Seite 1122--1130. New York, NY, USA, ACM, (2012)
M. Grimnes. EKAW 2010 Demo & Poster Abstracts. International Conference on Knowledge Engineering and Knowledge Management (EKAW-10), 17th International Conference on Knowledge Engineering and Knowledge Management, October 11-15, Lisbon, Portugal, -, (Oktober 2010)Best Poster.
P. Teufl, und G. Lackner. 10th International Conference on Knowledge Management and Knowledge Technologies 1–3 September 2010, Messe Congress Graz, Austria, Seite 18 - 18. (2010)
C. Rieß, N. Heino, S. Tramp, und S. Auer. Proceedings of the 9th International Semantic Web Conference (ISWC2010), Berlin / Heidelberg, Springer, (2010)
S. Baluja, D. Ravichandran, und D. Sivakumar. Proceeding of the International Conference on Knowledge Discovery and Information Retrieval (KDIR 2009), INSTICC, (6-8 10 2009)
B. Elliott, E. Cheng, C. Thomas-Ogbuji, und Z. Ozsoyoglu. Proceedings of the 2009 International Database Engineering & Applications Symposium, Seite 31--42. New York, NY, USA, ACM, (2009)
S. Schoenmackers, O. Etzioni, und D. Weld. EMNLP '08: Proceedings of the Conference on Empirical Methods in Natural Language Processing, Seite 79--88. Morristown, NJ, USA, Association for Computational Linguistics, (2008)
G. Grimnes, P. Edwards, und A. Preece. Proceedings of the 5th European Semantic Web Conference (ESWC 2008), Volume 5021 von Lecture Notes in Computer Science, Seite 303-317. Springer, (2008)
G. Forman, und E. Kirshenbaum. CIKM '08: Proceeding of the 17th ACM conference on Information and knowledge management, Seite 1221--1230. New York, NY, USA, ACM, (2008)
S. Gelly, und D. Silver. ICML '07: Proceedings of the 24th international conference on Machine learning, Seite 273--280. New York, NY, USA, ACM Press, (2007)
F. Wu, und D. Weld. CIKM '07: Proceedings of the sixteenth ACM conference on Conference on information and knowledge management, Seite 41--50. New York, NY, USA, ACM, (2007)
J. Lehmann. Machine Learning and Data Mining in Pattern Recognition, 5th International Conference, MLDM 2007, Leipzig, Germany, July 18-20, 2007, Proceedings, Volume 4571 von Lecture Notes in Computer Science, Seite 883--898. Springer, (2007)
K. Dellschaft, und S. Staab. In Proceedings of the 5th International Semantic Web Conference (ISWC2006), Volume 4273 von LNCS, Athens, GA, USA, (November 2006)