News and Events

ICDS Events

ICDS hosts a wide range of events, from training sessions on using our high-performance computing system to seminars about the latest topics in computational research. Here, you will find a list of upcoming ICDS events, as well as other events that may be of interest to the computational and data sciences community. Sign up for our mailing list to receive alerts about our events.

Want to learn what ICDS researchers are working on? Check out our Seminar series.

Science Communication Plenary

Date: Wednesday, October 23

Time: 4:00 p.m.

Location: Heritage Hall, HUB-Robeson Center

National journalists discuss how the media is changing and what it means for communicating science to the public and policymakers. They will share their personal perspectives on how to get your stories told, what makes a good science story, as well as “dos and don’ts” of dealing with journalists. A Q&A and reception with light refreshments will follow. This event is being organized by the Institutes of Energy and the Environment. The plenary will also be livestreamed. Participating Journalists:

  • David Malakoff, Science Magazine
  • Wudan Yan, Freelance
  • Clinton Parks, Freelance
  • Bob Marshall, New Orleans Journalist

Register or Learn More

University Libraries to offer data visualization session Oct. 28

Date: Monday, October 28–Monday, October 28

Time: 1:00 p.m.–2:00 p.m.

Location: Pattee Library and online on Zoom

On Oct. 28, Penn State University Libraries will offer a data visualization session highlighting services from several areas of the Libraries’ Research Informatics and Publishing department. The session will take place 1-2 p.m. in W315 Pattee Library, with remote viewing available online via Zoom. This session is aimed at providing an introduction to the resources and expertise available at the University Libraries in three areas: geospatial and statistical data visualization; interactive visualization using Jupyter Notebook; and data analytics and visualizations. Presenters will also discuss the one-on-one consultation services they provide, including:

Consultations are provided for the following software applications: ArcGIS Online, ArcMap, and ArcPro; JMP, RStudio, and Adobe Illustrator; MS SQL Server/BI and Tableau; and interactive visualizations using Jupyter Notebook, BinderHub, Zenodo, and ScholarSphere. Presenters include Tara Anthony, GIS specialist; Lizhao Ge, statistical information specialist; Briana Ezray, research data management librarian; Xuying Xin, data analyst; and Seth Erickson, software curation librarian. Following the session, an optional tour of the digital lab at Research Informatics and Publishing will be offered. The session is free and open to all Penn State students, staff and faculty. Advance registration is not required. For more information, contact Tara Anthony at 814-863-5753 or tll38@psu.edu.

Register or Learn More

How to Make AI Work

Date: Monday, October 28

Time: 2:00 p.m.

Location: Flex Theater, HUB-Robeson Center

Artificial intelligence (AI) is often claimed to have the promise of transforming and possibly taking over our society. But there seems to be little understanding of how it really works or its current limitations. Join us online (Zoom) or in person to learn more about the most popular and useful AI methodology, machine learning. Dr. Lee Giles, the David Reese Professor at the College of Information Sciences and Technology at Penn State, will discuss what a machine learning problem is and what it can do, as well as introduce a new machine learning model, deep learning. In an effort to provide context to artificial intelligence's power and limitations, the talk will highlight the basics of implementing AI into actual problems. It will also dive into the different classes and memory models of deep learning. Register now About the Presenter: Dr. C. Lee Giles is the David Reese Professor at the College of Information Sciences and Technology at the Penn State. His current research interests are in intelligent information processing systems. He is also graduate professor of computer science and engineering, courtesy professor of supply chain and information systems, and director of the intelligent systems research laboratory. He recently became a teaching and learning technology fellow and the interim associate dean of research for IST. He directs the Next Generation CiteSeer, CiteSeerx project and codirects the ChemXSeer project at Penn State. He has been associated with Columbia University, the University of Maryland, University of Pennsylvania, Princeton University, and the University of Trento. He is Fellow of the ACM, IEEE and the International Neural Network Society (INNS). He received the INNS Dennis Gabor Award for outstanding achievements in neural engineering and the IEEE Computational Intelligence Society's Pioneer Award in Neural Networks.


This event is being sponsored by ICS, Nittany AI Alliance, and Penn State IT. A separate event tailored toward undergraduate students will take place in the evening on Oct. 28. Students can register for that event using the "Register now" link above.  

XSEDE HPC Workshop: OpenMP

Date: Tuesday, November 5–Tuesday, November 5

Time: 11:00 a.m.–5:00 p.m.

XSEDE along with the Pittsburgh Supercomputing Center are pleased to announce a one day OpenMP workshop. This workshop is intended to give C and Fortran programmers a hands-on introduction to OpenMP programming. Attendees will leave with a working knowledge of how to write scalable codes using OpenMP. This event will be presented using the Wide Area Classroom(WAC) training platform.

Register or Learn More

“Semi-Supervised Learning Algorithm for Identifying High Priority Drug-Drug Interactions through Adverse Event Reports”

Date: Tuesday, November 5

Time: 10:30 a.m.–12:00 p.m.

Location: 233A HUB-Robeson Center and Streamed Live on Zoom

Watch the live stream on Zoom Add to Calendar Presenter: Soundar Kumara, Allen E. Pearce and Allen M. Pearce Professor of Industrial Engineering Abstract: We will discuss few of the major studies conducted by LISA (Laboratory of Intelligent Systems and Analytics) in healthcare using AI and Machine Learning. We will detail the drug-to-drug interactions (DDIs) work. Identifying drug-drug interactions (DDIs) is a critical enabler for reducing adverse drug events and improving patient safety. Generating proper DDI alerts during patient prescription workflow has the potential to prevent DDI-related adverse events, and such an alerting system has received much attention worldwide. However, to improve the contents of DDI alerts without causing alert fatigue still remains a challenge. One strategy is to establish a list of high-priority DDIs for alerting purposes though it is a resource-intensive task. In this study, we propose a machine learning framework to extract useful features from the FDA adverse event reports, and then identify potential high-priority DDIs using an autoencoder-based semi-supervised learning algorithm. The experimental results demonstrate the effectiveness of using adverse event feature representations in differentiating high- and low-priority DDIs. Additionally, the proposed algorithm utilizes stacked autoencoders and weighted support vector machine to boost classification performance, which outperforms other competing methods in terms of F-measure and AUC score. This framework integrates multiple information sources, leverages domain knowledge and clinical evidence, and provides a practical approach to pre-screen high-priority DDI candidates for use in DDI alerting systems. The talk will be more application based.

ACI Training Series Logo

Intermediate HPC training for ICS-ACI users

Date: Wednesday, November 6

Time: 10:00 a.m.–11:30 a.m.

Location: W203 Millennium Science Complex

Register or Learn More

Complex Adaptive Systems Conference

Date: Wednesday, November 13–Friday, November 15

Location: Penn State Great Valley

Artificial Intelligence (AI), machine learning methods, big data, and data analytics are vital for maintaining key systems, including smart cities, smart grids, connected autonomous vehicles, smart medical devices, wearable sensors and connected home-monitoring systems. Designing these continuously evolving systems requires a variety of perspectives to address modern societal challenges. Penn State Great Valley School of Professional Studies will host the 2019 Complex Adaptive Systems Conference, bringing together researchers from academia, industry and government to discuss applications of computational intelligence and machine learning methods to address challenges in cyber physical systems and sociotechnical systems.

Register or Learn More

Seminar: Scalable fixed-mesh method for massively parallel simulations of solid and fluid problems

Date: Wednesday, November 13

Time: 2:00 p.m.

Location: 233B HUB-Robeson Center

This ICS-sponsored seminar will showcase the work of Koji Nishiguchi, a collaborator of Christian Peco Regales, assistant professor of engineering science and mechanics and ICS Associate. Refreshments will be provided. No registration necessary. 

Add to Calendar

Abstract: In recent years, in the automotive industry, weight reductions are indispensable for complying with carbon dioxide emission regulations. Although automotive companies have been mainly using steel sheets, they want to employ multi-structures including extrusions, castings, or 3D printings of aluminum alloy or resin to achieve weight reductions. However, the structural design will be more complex because multi-material structures have a higher degree of geometric freedom than sheet metal structures. Therefore, numerical simulations need to play a more critical role in designing optimal vehicle structures. For the last several decades, a Lagrangian finite element method (FEM) using mainly shell formulation has been the de facto standard in the automotive industry. However, shell formulation cannot numerically model the multi-material structures mentioned above because they do not have a constant thickness. Thus, the continuum formulation has to be applied, but this approach poses two computational problems. The first problem is that an enormous number of finite elements using continuum formulation is required to discretize the multi-material structures spatially. A scalable method in a massively parallel environment is indispensable for this simulation. Secondly, we need to spend more than a month to generate the finite element mesh of a car body. Therefore, it is challenging to investigate many patterns of vehicle structures. Considering the background as mentioned above, we focus on a Eulerian finite volume method (FVM) [1] based on continuum formulation [2] using a scalable hierarchical Cartesian mesh method [1]. This Eulerian FVM [1] has the following three advantages. The first one is good scalability [1] in a massively parallel computing environment. Secondly, we can easily generate the computational mesh of a car body only within 10 minutes. We will demonstrate the stiffness analysis of a body-in-white structure, which is spatially discretized by approximately 200 million cells and was computed using 104,520 cores on the K computer. Thirdly, the proposed Eulerian method is easy to couple a conventional finite volume fluid solver. In future work, we plan to conduct car crash simulations using many patterns of multi-material vehicle structures to study ultralight vehicle structures. [1] K. Nishiguchi 2019 https://doi.org/10.1002/nme.5954  [2] K. Nishiguchi 2018 https://doi.org/10.1002/nme.5790

IBM AI Immersion Workshops

Date: Wednesday, November 13–Thursday, November 14

Location: Business Building

ICS, in partnership with Nittany AI Alliance and Penn State IT, is pleased to announce that IBM will be the first industry leader in the AI Immersion series that will be giving AI and data science workshops on the University Park campus. IBM will host five different workshops on November 13 and 14, showing researchers, staff members, and undergraduate students how to use several tools within the IBM Watson Services suite. Seating is limited to 20 for each workshop, and advance registration is required. Due to the hands-on nature of this programming, live streaming will not be available.   Researcher Session 1: “Using Computer Vision for University Research” 9:30-11:00 a.m., Thursday, Nov. 14 217 Business Building Learn about the many applications of computer vision to research, from satellite to cellular imagery, and how you can apply this to your own work. Register for Researcher Session 1   Researcher Session 2: “End-to-End Data Science with Watson Studio” Noon-1:30 p.m., Thursday, Nov. 14 217 Business Building Learn a comprehensive approach to data science leveraging IBM's Watson Studio interface, and how to use image or natural language classifier models in your work. Register for Researcher Session 2   Staff Member Session: “A ‘No-logon or Programming Required’ Tour of Watson AI Services” 3:00-4:30 p.m., Wednesday, Nov. 13 122 Business Building Get a hands-on lesson in how to use many tools available through IBM's Watson AI services, including speech, language, tone, and image analysis. Register for Staff Session   Undergraduate Student Session 1: “End-to-End Data Science with Watson Studio” 6:00-7:20 p.m., Wednesday, Nov. 13 217 Business Building   Undergraduate Student Session 2: “A ‘No-logon or Programming Required’ Tour of Watson AI Services” 7:30-9:00 p.m., Wednesday, Nov. 13 217 Business Building   Register for either Student Session

Supercomputing 2019

Date: Sunday, November 17–Friday, November 22

Location: Denver, Colorado

From the SC19 Website:

HPC touches lives everywhere – every day. And today, our work in HPC is more essential than ever, driven by an urgent need to provide computational solutions for the world’s greatest challenges from precision medicine and agricultural technologies to autonomous vehicles in smart cities and renewable energy. The impact of HPC goes beyond traditional research boundaries to enhance our daily lives. Be part of the HPC revolution at SC19. The future is now. HPC is now.

Register or Learn More

A Research Software Developer’s Toolkit

Date: Wednesday, November 20

Time: 11:00 a.m.–12:00 p.m.

Location: W203 Millennium Science Complex and Online via Zoom

Software is an indispensable tool for researchers using advanced or high-performance computing methods in their work. It enables them to analyze data sets, develop simulations and visualizations, and build sophisticated models. Yet the value of software developed by researchers is sometimes overlooked. This workshop is oriented toward the unique concerns of software development in the context of academic research. This workshop aims to provide a synoptic overview and venue to discuss aspects of research software development such as citation, software publishing, reproducibility, documentation, and code reuse. Attendee Prerequisites: Attendees do not need familiarity with a specific programming language or a particular disciplinary background. Instead, this workshop is tailored to researchers of all ranks and disciplines who develop software in the course of their work, who aim to promote the reuse of their code by the broader research community, and who are interested in advancing software as a scholarly (i.e. citable) product. Practices and platforms covered in the workshop:

  • Open Source Initiative (OSI) licenses
  • Tools for supporting reproducibility (BinderHub, ReproZip)
  • Repositories for creating citable software packages (Zenodo, ScholarSphere)
  • Code documentation standards (CodeMeta)
About the Speaker: Seth Erickson is the Software Curation Librarian at Penn State University Libraries. In this role, he supports digital scholarship at Penn State by developing library services for preserving, accessing, and reusing research software. Erickson received his Ph.D. in Information Studies from University of California, Los Angeles, where he studied the software development practices of computational physicists. His research focuses on the social dimensions of research software development and concerns for openness in scientific computing.

Register or Learn More

extreme science and engineering discovery workshop series at psu ics

Big Data Workshop on XSEDE

Date: Tuesday, December 3–Wednesday, December 4

Time: 11:00 a.m.–5:00 p.m.

Location: 424 Ag Administration Building

Learn how to conduct big data analyses on the XSEDE platform. The two-day workshop will include sessions on Spark, Hadoop, Machine Learning, Deep Learning, and Bridges. This session is being presented by the Pittsburgh Supercomputing Center, and is being broadcast to the University Park campus using the Wide Area Classroom (WAC) training platform. Registration Deadline: Friday, Nov. 29, at Noon

Register or Learn More

SEA’s Improving Scientific Software Conference 2020

Date: Monday, April 27–Friday, May 1

Location: NCAR Center Green Campus, Boulder, CO

The 2020 annual SEA’s Improving Scientific Software conference will take place in Boulder, CO at the NCAR Center Green Campus from the afternoon of Monday April 27th to Friday May 1st

We are soliciting talks, tutorials and papers on Improving Scientific Software related to any of the following: Influence of computer architecture on scientific software design, including but not limited to:
  •  Modern architectures (such as GPU, ARM, etc)
  • Post-modern architectures (such as Quantum Computing, Neuromorphic, etc)
  • Extreme Heterogeneity (intra-node and inter-system)
  • Edge computing
  • Communication/computation overlap
  • Performance, Portability & Productivity
  • Modern tools for
  • Data Analysis, Processing and Visualization
  • Scientific Workflows: Purpose and Product Review.
  • Machine learning for Scientific Computing
  • Containers in scientific software
  • Leveraging Cloud Computing Resources for HPC Development and Operations