Techniques provide users with insights into high-dimensional datasets
Every dataset in the observable universe has a fundamental geometry or shape to it, but that structure can be highly complicated. To make it easier to visualize complicated datasets, a Dartmouth research team has created HyperTools-- an open-source software package that leverages a suite of mathematical techniques to gain intuitions about high-dimensional datasets through the underlying geometric structures they reflect. The findings are published in the Journal of Machine Learning Research.
This is a visualization using HyperTools to represent the content of Wikipedia articles. Each dot represents a single Wikipedia article (from a set of 3,000 randomly chosen articles). The dot positions reflect what the articles are about (nearby dots are about similar topics), and the dot colors reflect automatically discovered "clusters" of articles that are about similar themes. To view a 3-D animation of this data (GIF file), go to: http://discovery.dartmouth.edu/~jmanning/hypertools_gifs/wiki.gif
Credit: Static image by Contextual Dynamics Laboratory, Dartmouth College
HyperTools can be used to transform data into visualizable shapes or animations, which can be used to: compare different datasets, gain insights into underlying patterns in an intuitive way, make generalizations across datasets, and develop and test theories relating to the Big Data.
"The datasets we're faced with as modern scientists can be enormously complex, often reflecting many interacting components," explains senior author, Jeremy R. Manning, an assistant professor of psychological and brain sciences and director of the Contextual Dynamics Lab at Dartmouth.
"Our tool turns complex data into intuitive 3-D shapes that can be visually examined and compared. Essentially, we are leveraging the visual system's amazing ability to find patterns in the world around us to also find patterns in complex scientific data."
The researchers demonstrate how HyperTools can be applied to various types of data. In the paper, they showcase visualizations of: brain activity, movie frames and brain responses to watching those frames; changes in temperature measurements across the Earth's surface from 1875 to 2013; and the thematic content of political tweets issued by Hillary Clinton and Donald Trump during the 2016 US presidential campaign.
In addition to using HyperTools to directly understand the geometric structure of data, the insights revealed by the tool can also be used to guide the development of machine learning algorithms. For example, the data visualizations can reveal how different types of observations form structured distinct clusters (e.g. Trump tweets vs. Clinton tweets) that could be used to understand the similarities and differences between groups.
As part of the HyperTools toolbox, Manning's lab continues to develop and release other types of geometric visualization analyses, including the recently launched text analyses.
Manning is available for comment at: email@example.com.
The study's other authors include Dartmouth postdoctoral researcher Andrew Heusser and graduate student Kirsten Ziman (lead co-authors) and graduate student Lucy Owen, all members of Manning's lab.
GIFs and hi-res still images are available upon request.
Amy D. Olson | EurekAlert!
Reversing cause and effect is no trouble for quantum computers
20.07.2018 | Centre for Quantum Technologies at the National University of Singapore
Study suggests buried Internet infrastructure at risk as sea levels rise
18.07.2018 | University of Wisconsin-Madison
A new manufacturing technique uses a process similar to newspaper printing to form smoother and more flexible metals for making ultrafast electronic devices.
The low-cost process, developed by Purdue University researchers, combines tools already used in industry for manufacturing metals on a large scale, but uses...
For the first time ever, scientists have determined the cosmic origin of highest-energy neutrinos. A research group led by IceCube scientist Elisa Resconi, spokesperson of the Collaborative Research Center SFB1258 at the Technical University of Munich (TUM), provides an important piece of evidence that the particles detected by the IceCube neutrino telescope at the South Pole originate from a galaxy four billion light-years away from Earth.
To rule out other origins with certainty, the team led by neutrino physicist Elisa Resconi from the Technical University of Munich and multi-wavelength...
For the first time a team of researchers have discovered two different phases of magnetic skyrmions in a single material. Physicists of the Technical Universities of Munich and Dresden and the University of Cologne can now better study and understand the properties of these magnetic structures, which are important for both basic research and applications.
Whirlpools are an everyday experience in a bath tub: When the water is drained a circular vortex is formed. Typically, such whirls are rather stable. Similar...
Physicists working with Roland Wester at the University of Innsbruck have investigated if and how chemical reactions can be influenced by targeted vibrational excitation of the reactants. They were able to demonstrate that excitation with a laser beam does not affect the efficiency of a chemical exchange reaction and that the excited molecular group acts only as a spectator in the reaction.
A frequently used reaction in organic chemistry is nucleophilic substitution. It plays, for example, an important role in in the synthesis of new chemical...
Optical spectroscopy allows investigating the energy structure and dynamic properties of complex quantum systems. Researchers from the University of Würzburg present two new approaches of coherent two-dimensional spectroscopy.
"Put an excitation into the system and observe how it evolves." According to physicist Professor Tobias Brixner, this is the credo of optical spectroscopy....
13.07.2018 | Event News
12.07.2018 | Event News
03.07.2018 | Event News
20.07.2018 | Power and Electrical Engineering
20.07.2018 | Information Technology
20.07.2018 | Materials Sciences