Whereas people learn many different types of knowledge from diverse experiences over many years, most current machine learning systems acquire just a single function or data model from just a single data set. We propose a never-ending learning paradigm for machine learning, to better reflect the more ambitious and encompassing type of learning performed by humans. As a case study, we describe the Never-Ending Language Learner (NELL), which achieves some of the desired properties of a never-ending learner, and we discuss lessons learned. NELL has been learning to read the web 24 hours/day since January 2010, and so far has acquired a knowledge base with over 80 million confidence-weighted beliefs (e.g., servedWith(tea, biscuits)). NELL has also learned millions of features and parameters that enable it to read these beliefs from the web. Additionally, it has learned to reason over these beliefs to infer new beliefs, and is able to extend its ontology by synthesizing new relational predicates. NELL can be tracked online at http://rtw.ml.cmu.edu, and followed on Twitter at @CMUNELL.

This paper presents a parallel visualization pipeline implemented at the Pittsburgh Supercomputing Center (PSC) for studying the largest earthquake simulation ever performed. The simulation employs 100 million hexahedral cells to model 3D seismic wave propagation of the 1994 Northridge earthquake. The time-varying dataset produced by the simulation requires terabytes of storage space. Our solution for visualizing such terascale simulations is based on a parallel adaptive rendering algorithm coupled with a new parallel I/O strategy which effectively reduces interframe delay by dedicating some processors to I/O and preprocessing tasks. In addition, a 2D vector field visualization method and a 3D enhancement technique are incorporated into the parallel visualization framework to help scientists better understand the wave propagation both on and under the ground surface. Our test results on the HP/Compaq AlphaServer operated at the PSC show that we can completely remove the I/O bottlenecks commonly present in time-varying data visualization. The high-performance visualization solution we provide to the scientists allows them to explore their data in the temporal, spatial, and variable domains at high resolution. The new high-resolution explorability, likely not available to most computational science groups, will help lead to many new insights.

The primary design goal for P3D has been to produce a metafile format which can support the needs of scientific visualization while remaining compatible with a wide range of common renderers. To this end, rendering features which are available on only a few renderers and cannot easily be emulated have been excluded from P3D. P3D is based on the Common Lisp programming language with a small number of extensions for the description of geometry. The programmability of P3D greatly eases the task of adapting existing model generators to produce P3D, in the same fashion that the programmability of the Postscript page description language eases the task of modifying code to generate Postscript. Further, programmability allows knowledge of the particular scientific domain of the model to be incorporated into the metafile. This method provides easy representation of directed acyclic graphs and complete programmability to facilitate interfaces to new model generators, without the introduction of a new and unfamiliar language.>