September 17, 2019 - Webinar
Join us as we continue this webinar series specifically designed for the community by the community with the goal to share knowledge, spark innovation, and further build and link the relationships within our HPCC Systems community.
Featured topics include the work presented by three of our summer interns and one of our security architects from the platform team:
- Vannel Zeufack, Masters Student, CSE, Kennesaw State University - Developing and Assessing Unsupervised Anomaly Detections Methods using HPCC Systems
Vannel has been researching various log analysis techniques to detect abnormal activities on computing/network systems alongside his professor at KSU. His aim is to adopt a number of machine learning and big data analysis techniques, to implement an algorithm that has the ability to detect unknown cybersecurity threats. The ideas for his project are based on the paper Experience Report: System Log Analysis for Anomaly Detection by Shilin He, Jieming Zhu, Pinjia He and Michael R. Lyu.
- Farah Alshanik, PhD Student, CS, Clemson University - Domain Based Common Words List Using High Dimensional Representation of Text
Farah Alshanik is a Ph.D. student of computer science in Clemson University. She received her B.S from Jordan University of Science and Technology. She is working with Dr.Amy Apon as a Research Assistance in Data Intensive Computing Ecosystems (DICE) Lab. Her interest is focused on applying high performance computing to machine learning problems.
The aim of Farah's internship project is to use a text vectors bundle (CBOW) with HPCC Systems to find the common words for any datasets. Her project is based on the hypothesis that eliminating domain based common words will enhance the performance of the classification methods used as well as improve the results of topic modeling. The ability of HPCC Systems to massively scale-up and its fast distributed data storage will enhance the performance of the methodology.
- Robert Kennedy, PhD Student, CS, Florida Atlantic University- Expanding HPCC Systems Deep Neural Network Capabilities - Create HPCC Systems VM on Hyper V
Robert Kennedy is a second year Ph.D. student in CS at Florida Atlantic University with research interests in Deep Learning and parallel and distributed computing. His current research is in improving distributed deep learning by implementing and optimizing distributed algorithms.
Robert has been researching and developing GPU accelerated Deep Learning algorithms on HPCC Systems. In his proposal, Robert talks about how GPU acceleration vastly improves Deep Learning training time. His work will produce the first GPU accelerated library (to his knowledge) and expand our deep neural network capabilties. Creating an HPCC Systems VM on Hyper V as part of this project, will increase the number of configurations on which HPCC Systems can be deployed and provide the building blocks needed for the possible future development of different distributed configurations that we don't currently provide, such as model parallelism and enabling HPCC Systems to Deep Learn using asynchronous algorithms.
- Russ Whitehead, Architect, LexisNexis Risk Solutions - Security and HPCC Systems - Cryptographic ECL Standard Library
Russ Whitehead (William) is an HPCC Systems Software Architect and has a BS degree in Computer Science from University of Florida, and an MBA from the University of Miami. His background is operating systems development, network management and voice recognition, and he has been a LexisNexis employee and a platform team member since May 2008. His top responsibility is the HPCC security framework, which he has been contributing to since 2012.
Submit a talk for an upcoming episode!
- Have a new success story to share?
- Want to pitch a new use case?
- Have a new HPCC Systems application you want to demo?
- Want to share some helpful ECL tips and code sample?
- Have a new suggestion for the roadmap?
It’s easy! All you need to do is submit a talk title and brief abstract to email@example.com. If chosen, you will be asked to present remotely for an upcoming 20-minute tech talk.