Robert Brunner

About

Robert Brunner is a professor of accounting at Gies College of Business and serves as the associate dean for innovation and chief disruption officer. He joined the College in 2017 and holds the title of Arthur Andersen fellow. Brunner has a diverse academic background, with a bachelor's degree in physics from Purdue University, a PhD in astrophysics from Johns Hopkins University, and postdoctoral work at the California Institute of Technology. His research and professional interests include data science, machine learning, and their applications in various fields such as astronomy and finance. Brunner has held multiple affiliate appointments across departments including Computer Science, Electrical and Computer Engineering, Physics, and Statistics, as well as at the Beckman Institute and the National Center for Supercomputing Applications. His work encompasses innovative approaches to data analysis, visualization, and the integration of disruptive technologies into business and academic environments.

Research topics

• Computer Science
• Artificial Intelligence
• Machine Learning
• Natural Language Processing
• Data Mining
• Algorithm
• Parallel computing
• Theoretical computer science
• Geography
• Programming language

Selected publications

• The Dark Energy Survey: more than dark energy – an overview

  Monthly Notices of the Royal Astronomical Society · 2016-03-21 · 995 citations

  articleOpen access

  This overview paper describes the legacy prospect and discovery potential of the Dark Energy Survey (DES) beyond cosmological studies, illustrating it with examples from the DES early data. DES is using a wide-field camera (DECam) on the 4 m Blanco Telescope in Chile to image 5000 sq deg of the sky in five filters (grizY).

  PublisherOA PDFDOI

• Extended Isolation Forest

  IEEE Transactions on Knowledge and Data Engineering · 2019-10-31 · 448 citations

  articleOpen accessSenior author

  We present an extension to the model-free anomaly detection algorithm, Isolation Forest. This extension, named Extended Isolation Forest (EIF), resolves issues with assignment of anomaly score to given data points. We motivate the problem using heat maps for anomaly scores. These maps suffer from artifacts generated by the criteria for branching operation of the binary tree. We explain this problem in detail and demonstrate the mechanism by which it occurs visually. We then propose two different…

  PublisherOA PDFDOI

• Star–galaxy classification using deep convolutional neural networks

  Monthly Notices of the Royal Astronomical Society · 2016-10-14 · 217 citations

  articleOpen accessSenior author

  Most existing star–galaxy classifiers use the reduced summary information from catalogues, requiring careful feature extraction and selection. The latest advances in machine learning that use deep convolutional neural networks (ConvNets) allow a machine to automatically learn the features directly from the data, minimizing the need for input from human experts. We present a star–galaxy classification framework that uses deep ConvNets directly on the reduced, calibrated pixel values. Using data f…

  PublisherOA PDFDOI

• Galaxy clustering, photometric redshifts and diagnosis of systematics in the DES Science Verification data

  Monthly Notices of the Royal Astronomical Society · 2015-12-09 · 90 citations

  articleOpen access

  We study the clustering of galaxies detected at i < 22.5 in the Science Verification observations of the Dark Energy Survey (DES). Two-point correlation functions are measured using 2.3 10 6 galaxies over a contiguous 116 deg 2 region in five bins of photometric redshift width z = 0.2 in the range 0.2 < z < 1.2. The impact of photometric redshift errors is assessed by comparing results using a template-based photo-z algorithm (BPZ) to a machine-learning algorithm (TPZ). A companion paper present…

  PublisherOA PDFDOI

• Machine learning and cosmological simulations – II. Hydrodynamical simulations

  Monthly Notices of the Royal Astronomical Society · 2016-02-01 · 61 citations

  articleOpen accessSenior author

  We extend a machine learning (ML) framework presented previously to model galaxy formation and evolution in a hierarchical universe using N-body + hydrodynamical simulations. In this work, we show that ML is a promising technique to study galaxy formation in the backdrop of a hydrodynamical simulation. We use the Illustris simulation to train and test various sophisticated ML algorithms. By using only essential dark matter halo physical properties and no merger history, our model predicts the ga…

  PublisherOA PDFDOI

Recent grants

• NSF CDSE: Enabling Precise Constraints on Dark Energy

  NSF · $667k · 2013–2018

Frequent coauthors

• Gordon T. Richards

  91 shared

• Donald P. Schneider

  81 shared

• Patrick B. Hall

  77 shared

• D. E. vanden Berk

  76 shared

• Neta A. Bahcall

  Princeton University

  72 shared

• Michael A. Strauss

  Princeton University

  68 shared

• Andrew J. Connolly

  University of Washington

  60 shared

• David H. Weinberg

  The Ohio State University

  58 shared

Labs

• Disruption LabPI

Awards & honors

• Arthur Andersen Faculty Fellow

Similar researchers at University of Illinois Urbana-Champaign

• Matias Carrasco Kindh-102
• Ciao-Wei Chenh-22
• Fei Duh-14