Author Archives: Christof Teuscher

OPENING: REU Site Program Administrator

We are seeking an undergraduate student administrator to help us run the NSF-funded Research Experience for Undergraduates (REU) Site on “Computational Modeling Serving the City.”

AS AN REU SITE PROGRAM ADMINISTRATOR, YOU WILL:

  • Communicate with potential and admitted students via e-mail and phone
  • Coordinate recruiting efforts
  • Design and maintain online application forms
  • Prepare application packages for review
  • Plan and organize meetings and events
  • Arrange student travel, lodging, transportation
  • Analyze and visualize data
  • Prepare flyers, presentations, and advertising materials for the program
  • Maintain the WordPress website

Continue reading →

New Paper: Proximal Policy Optimization for Radiation Source Search

Proctor, P.; Teuscher, C.; Hecht, A.; Osiński, M. Proximal Policy Optimization for Radiation Source Search. Journal of Nuclear Engineering, 2:368-397, 2021. https://doi.org/10.3390/jne2040029

Rapid search and localization for nuclear sources can be an important aspect in preventing human harm from illicit material in dirty bombs or from contamination. In the case of a single mobile radiation detector, there are numerous challenges to overcome such as weak source intensity, multiple sources, background radiation, and the presence of obstructions, i.e., a non-convex environment. In this work, we investigate the sequential decision making capability of deep reinforcement learning in the nuclear source search context. A novel neural network architecture (RAD-A2C) based on the advantage actor critic (A2C) framework and a particle filter gated recurrent unit for localization is proposed. Performance is studied in a randomized 20×20 m convex and non-convex simulation environment across a range of signal-to-noise ratio (SNR)s for a single detector and single source. RAD-A2C performance is compared to both an information-driven controller that uses a bootstrap particle filter and to a gradient search (GS) algorithm. We find that the RAD-A2C has comparable performance to the information-driven controller across SNR in a convex environment. The RAD-A2C far outperforms the GS algorithm in the non-convex environment with greater than 95% median completion rate for up to seven obstructions.

IEEE Transactions on Parallel and Distributed Special Section on Non-Von Neumann Technologies Published

S. Pakin, K. Schuman, C. Teuscher. Special Section on Parallel and Distributed Computing Techniques for Non-Von Neumann Technologies, IEEE Transactions on Parallel and Distributed Systems (TPDS), 32(2), 2022, https://ieeexplore.ieee.org/xpl/tocresult.jsp?isnumber=9493664

IMMEDIATE OPENING: GRA Position in Radiation Detection and Localization

The objectives of this research project are to develop neuromorphic computing algorithms, architectures, and components capable of energy-efficient analysis of data from mobile radiation detection platforms. We have so far developed, implemented, and tested a neuromorphic isotope identification as well as a localization architecture. For the remainder of the project, the GRA will propose, implement, and test a novel architecture that combines the existing identification and localization modules.

The position is funded by the Defense Threat Reduction Agency (DTRA). The project is a collaboration with teams from the University of New Mexico.

QUALIFICATIONS

  • The ideal candidate has experience in reinforcement learning, neural networks, memristors, crossbars, and optimization techniques.
  • Must be enrolled in the ECE or CS MS or PhD program at PSU for the fall ’21, winter ’22, and spring ’22.
  • Excellent Python programming skills.
  • Interested in far-reaching cutting-edge interdisciplinary research.
  • Outstanding academic records.
  • Excellent written and verbal communication skills in English.
  • Highly motivated, responsible, independent, with outstanding work ethics.
  • Visionary, creative, outside-the-box thinker.

WHAT YOU GET

A place to invent, design, create, investigate, support and advice, an unconventional lab environment, free coffee, a GRA stipend, tuition, a foosball table, access to a powerful research compute server, a unique team, opportunities to collaborate with researchers from other fields.

WHAT WE DO

The mission of teuscher.:Lab is review the foundations of computer technology to help solve tomorrow’s technological and societal problems. We use a radical interdisciplinary approach and apply tools from computer science, computer engineering, physics, biology, complex systems science, and cognitive science to the study and the design of next generation computing models and architectures. Our research and education have global impact. We educate lifelong learners through academic excellence.

APPLICATION

Send application materials to teuscher@pdx.edu. Review will begin immediately. The position remains open until filled. Portland State University is an Equal Opportunity/Affirmative Action Employer.