Tag

big data

XSEDE: Python Tools for Data Science

By |

OVERVIEW

Python has become a very popular programming language and software ecosystem for work in Data Science, integrating support for data access, data processing, modeling, machine learning, and visualization. In this webinar, we will describe some of the key Python packages that have been developed to support that work, and highlight some of their capabilities. This webinar will also serve as an introduction and overview of topics addressed in two Cornell Virtual Workshop tutorials, available at https://cvw.cac.cornell.edu/pydatasci1 and https://cvw.cac.cornell.edu/pydatasci2 .

See https://portal.xsede.org/course-calendar/-/training-user/class/2467/session/4161 for more information and registration

 

Register via the XSEDE Portal:

If you do not currently have an XSEDE Portal account, you will need to create one:

https://portal.xsede.org/my-xsede?p_p_id=58&p_p_lifecycle=0&p_p_state=maximized&p_p_mode=view&_58_struts_action=%2Flogin%2Fcreate_account

Should you have any problems with that process, please contact help@xsede.org and they will provide assistance.

 

XSEDE HPC HPC Summer Boot Camp

By |

OVERVIEW

XSEDE, along with the Pittsburgh Supercomputing Center is pleased to present a Hybrid Computing workshop.

This 4 day event will include MPI, OpenMP, GPU programming using OpenACC and accelerators.

This workshop will be remote to desktop only due to the COVID-19 pandemic.  When the registration has filled, there will be no more students added due to our current limits.

The schedule can be found here:  https://www.psc.edu/resources/training/xsede-hpc-workshop-june-8-11-2021-summer-boot-camp/

 

Register via the XSEDE Portal:

https://portal.xsede.org/course-calendar/-/training-user/class/2338/session/4002

If you do not currently have an XSEDE Portal account, you will need to create one:

https://portal.xsede.org/my-xsede?p_p_id=58&p_p_lifecycle=0&p_p_state=maximized&p_p_mode=view&_58_struts_action=%2Flogin%2Fcreate_account

Should you have any problems with that process, please contact help@xsede.org and they will provide assistance.

Questions

Please address any questions to Tom Maiden at tmaiden@psc.edu.

GIS Fundamentals – Spatial Database, PostGIS

By |

PostGIS, built on top of PostgreSQL, is the most powerful open-source relational database for managing spatial data. In this workshop we will cover the basic concept of spatial databases, learn about setting PostGIS, and understand how PostGIS can help us manage large volumes of vector data spread over multiple tables and geometries efficiently.  We will also touch upon topics such as spatial indexing and the capabilities of PostGIS for other data models for 2-D GIS such as the network and raster data model.

GIS Fundamentals – V (Spatial Database – PostGIS)

By |

This is the fifth workshop in a series of workshops we are offering this semester on the fundamentals of GIS. Each workshop covers one or two key elements of GIS and is somewhat self-contained. The focus is on conceptual details that can provide sufficient preparation for applications, but we will also touch upon the technical aspects.

In this workshop we will cover the basic concepts of spatial databases and learn about setting up and using PostGIS, an open source spatial database built on top of PostgreSQL, along with R for vector data analysis. We will also touch upon topics such as spatial indexing, query processing and the capabilities of PostGIS for other data models such as the network and raster data model. This is a hands-on workshop and the instructor will use a Mac machine. If you intend to use a Windows or Linux machine please get in touch with the instructor before the workshop at manishve@umich.edu.

CSCAR Workshop: CoreLogic property data

By |
The University of Michigan library system has licensed a large data set containing real estate transactions, deeds, and property tax records for the United States.  The data were collected by the commercial vendor CoreLogic, and our license allows UM researchers to use the data for research purposes.  These data are of potential interest to researchers in many fields, as they capture spatial and temporal real estate market conditions, taxing practices, and the physical states of millions of residential structures in the US.
 
In this workshop, participants will learn to create geographical subsets of the data, seamlessly integrate it in workflow, and see examples of research questions where the data can be useful. Participants should know Python and R.

Balzano wins NSF CAREER award for research on machine learning and big data involving physical, biological and social phenomena

By | General Interest, Happenings, News, Research

Prof. Laura Balzano received an NSF CAREER award to support research that aims to improve the use of machine learning in big data problems involving elaborate physical, biological, and social phenomena. The project, called “Robust, Interpretable, and Efficient Unsupervised Learning with K-set Clustering,” is expected to have broad applicability in data science.

Modern machine learning techniques aim to design models and algorithms that allow computers to learn efficiently from vast amounts of previously unexplored data, says Balzano. Typically the data is broken down in one of two ways. Dimensionality-reduction uses an algorithm to break down high-dimensional data into low-dimensional structure that is most relevant to the problem being solved. Clustering, on the other hand, attempts to group pieces of data into meaningful clusters of information.

However, explains Balzano, “as increasingly higher-dimensional data are collected about progressively more elaborate physical, biological, and social phenomena, algorithms that aim at both dimensionality reduction and clustering are often highly applicable, yet hard to find.”

Balzano plans to develop techniques that combine the two key approaches used in machine learning to decipher data, while being applicable to data that is considered “messy.” Messy data is data that has missing elements, may be somewhat corrupted, or is filled heterogeneous information – in other words, it describes most data sets in today’s world.

Balzano is an affiliated faculty member of both the Michigan Institute for Data Science (MIDAS) and the Michigan Institute for Computational Discovery and Engineering (MICDE). She is part of a MIDAS-supported research team working on single-cell genomic data analysis.

Read more about the NSF CAREER award…

Women in Big Data at Michigan Symposium

By |

Please join us for the Women in Big Data at Michigan symposium. This day-long symposium will highlight women data science researchers at U-M, provide resources and support for women pursuing careers in data science, a poster session, lunch time round table discussions, a faculty panel, and ample time for networking.

Please fill out the registration form if you plan to attend and consider submitting a poster. 

For more information, see the event page at https://midas.umich.edu/2018-wbdm/.

Keynote Speaker:

Xihong Lin
Henry Pickering Walcott Professor of Biostatistics
Harvard T.H. Chan School of Public Health

Dr. Lin’s research focuses on the development and application of statistical and computational methods to analyze high-throughput genetic and genomic data in epidemiological, environmental and clinical studies, and to analyze complex exposure and phenotype data in observational studies.

U-M Speakers:

Presenters Panel Participants
“Charting a Career in Data Science”
Jenna Wiens, Computer Science and Engineering Moderator: Liza Levina, Statistics
Snigdha Panagrahi, Statistics Bhramar Mukherjee, Biostatistics
Heather Mayes, Chemical Engineering Rada Mihalcea, Computer Science and Engineering
Danai Koutra, Computer Science and Engineering Amy Cohn, Industrial and Operations Engineering
Veronica Berrocal, Biostatistics Rocio Titiunik, Political Science
Maureen Sartor, DCMB Jennifer Linderman, Chemical Engineering

ACNN Big Data Neuroscience Workshop

By |

BIG DATA NEUROSCIENCE WORKSHOP

Organized by Advanced Computational Neuroscience Network (ACNN)

Registration

Come join the ACNN Big Data Neuroscience Workshop and enjoy:

❖ Keynotes and Invited Talks
❖ Data Sharing Initiatives
❖ Demonstration of Neuroscience Computational Platforms
❖ Reproducibility Best Practices
❖ Learning Environment for Students and Early-Career Researchers

Students, trainees, fellows, junior investigators from the Midwest as well outside academic institutions and industry partners are invited.

Pushing Mobile Inventions Forward Seminar: Fjola Helgadottir, PhD – Director of AI Therapy

By |

Fjola Helgadottir, PhD

Director of AI Therapy

Vancouver CBT Centre

 

Translating Clinical Psychology Treatments into Algorithms: Successes and Challenges

Abstract: Computerized therapy has the potential to revolutionize how evidence based psychological interventions are delivered to those who need them. Many of the recent advances in AI, from computer vision to natural language processing, will doubtlessly be integral components of future treatment systems.

There is a wide range of approaches to computerized therapy. Many research projects aim to replicate the face-to-face therapy experience. This seems like a natural approach, given that this is a longstanding and proven model of therapy. For example, these systems make use of avatars and chatbots. However, this approach may be misguided. Computer-based approaches and human therapists are fundamentally different, and designing one to mimic the other may not be optimal. The goal should be to find the most effective methods of targeting the key mechanisms that are paramount to change in mental health.

In this talk Dr. Helgadottir will take a look at computerized therapy from the perspective of a practicing clinical psychologist. She will review some of the advantages that computers have over human therapists, as well as considering limitations of these systems. As a practical example, she will explain how her online “Overcome social anxiety” program works and discuss promising results from recent clinical trials.

Bio: Dr Fjola Dogg Helgadottir is a Director at AI-Therapy, a registered psychologist at the Vancouver CBT Centre and previously a Senior Research Clinician at Department of Psychiatry, University of Oxford in the UK. She is a Chartered clinical psychologist within the British Psychological Society, and a registered psychologist with the UK Health and Care Professions Council and with the British Columbia College of Psychologists. Fjola has completed four degrees in psychology (see more professional qualifications). AI-Therapy grew out of her doctoral research, which was focused on innovative computer-based treatments for anxiety disorders.

Fjola has written extensively about online therapy, both in peer reviewed academic journals and conferences. She is an expert writer for Psychology Today with her open access blog Man vs Machine and is featured frequently in the Icelandic media. See Fjola’s publications for more details.

Fjola has received several major awards for her internationally recognized research, including Australia’s prestigious Tracy Goodall Early Career Award for Research Achievement. In addition, she has trained to the highest level as a clinical psychologist in Australia, and ran a successful private practice in Sydney. She currently provides consulting services on the topic of online psychology and psychiatry for her company AICBT Ltd, which has clients in Sydney, Australia; Oxford and London, UK; and Denver and New York in the USA.

MIDAS Learning Analytics Challenge Symposium

By |

Learning analytics is one of the research focus areas that MIDAS supports with its Challenge Awards.  Our long-term goal is to support this research area more broadly, using the Challenge Award projects as the starting point to build a critical mass.  This symposium offers a platform for all participants to explore collaboration opportunities and aims to attract more researchers to our hub.  It will feature in-depth presentations from two Challenge Award teams, and all participants are encouraged to submit posters on research related to Learning Analytics.

Agenda

9 am to 11:30 am: Welcome and Challenge Award presentations

11:30 am to 1 pm: Lunch, Poster Session, Networking [poster dimensions: up to 6ft wide X 4ft height]

1 to 2 pm: Panel discussion: The Future of Data Science for Learning Analytics at U-M

Panelists:

  • Steve DesJardins, Education, Public Policy
  • Cynthia Finelli, Engineering Education Research Program
  • Al Hero (Moderator), MIDAS, Electrical Engineering and Computer Science
  • Rada Mihalcea, Computer Science Engineering
  • Stephanie Teasley, Information

 

Please register online.  Please submit poster abstracts (< 300 words).  Submission Deadline: May 15.

For questions: midas-research@umich.edu.

Recommended Visitor Parking:  Palmer Parking StructurePalmer Drive, Ann Arbor