VIPR: an interactive tool for meaningful visualization of high-dimensional data
作者： Artur Dubrawski , Madalina Fiterau , Donghan Wang
DOI:
关键词: Web application 、 Service (systems architecture) 、 Projection (relational algebra) 、 Computer science 、 Decision support system 、 Cluster analysis 、 Artificial intelligence 、 Task (project management) 、 Machine learning 、 Visualization 、 Clustering high-dimensional data
摘要: Analysis, pattern discovery, and decision support all can benefit greatly from informative interpretable visualizations, especially of high-dimensional data. Informative Projection Ensemble (IPE) methodology has proven effective in finding renderings data that reveal hidden low-dimensional structures if such exist. In this demonstration, we present a powerful analysis tool uses IPE fundamental machine learning tasks: regression, classification, clustering. Our is an interactive web application operating on 2D 3D projections automatically selected by algorithms as for the user-specified task. It also provides RESTful APIs enabling remote users to seamlessly integrate our service with other tools easily extend its functionality. We show examples how it discover embedded
ijcai.org参考文章(4)
Madalina Fiterau, Artur Dubrawski, Informative Projection Recovery for Classification, Clustering and Regression international conference on machine learning and applications. ,vol. 1, pp. 15- 20 ,(2013) , 10.1109/ICMLA.2013.11
Rodolphe Jenatton, Julien Mairal, Guillaume Obozinski, Francis Bach, Optimization with Sparsity-Inducing Penalties ,(2011)
B. Shneiderman, The eyes have it: a task by data type taxonomy for information visualizations ieee symposium on visual languages. pp. 336- 343 ,(1996) , 10.1109/VL.1996.545307
Donghan Wang, Madalina Fiterau, Artur Dubrawski, Marilyn Hravnak, Gilles Clermont, Michael Pinsky, 797: INTERPRETABLE ACTIVE LEARNING IN SUPPORT OF CLINICAL DATA ANNOTATION Critical Care Medicine. ,vol. 42, ,(2014) , 10.1097/01.CCM.0000458294.39613.E1