Data Scientist
Data Scientist

Biography

Elise Bishoff joined Pacific Northwest National Laboratory (PNNL) in 2019 and currently supports the National Security Directorate as a data scientist. Her work at PNNL has covered areas of safety and security of machine learning models, natural language processing, record linkage on big data, model production, deep learning, robustness of computer vision models, and developing data science workshop materials.

Bishoff is also passionate about mentoring and helping others starting out their career in data science. She co-leads a Women in Data Science - Data Circles group to help women develop their data science careers. She believes that mentoring is at the heart of creating strong leaders at PNNL.

Research Interest

  • Safety and security of machine learning models
  • Model robustness
  • Computer vision
  • Machine learning
  • Deep learning
  • Natural language processing
  • Record linkage
  • Author name disambiguation

Education

  • MS in applied mathematics, University of Washington
  • BS in mathematics, Seattle Pacific University

Affiliations and Professional Service

  • PNNL STEM Ambassador, January 2021–Present
  • Co-Lead, Women in Data Science - Data Circles Book Club, July 2019–Present

Awards and Recognitions

  • Outstanding Performance Award, PNNL, 2021 and 2023

Publications

2023

  • Bishoff, E., Godfrey, C., McKay, M., & Byler, E. (2023). Quantifying the robustness of deep multispectral segmentation models against natural perturbations and data poisoning. In Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imaging XXIX (Vol. 12519, pp. 200-213). SPIE.
  • Godfrey, C., Bishoff, E., McKay, M., & Byler, E. (2023). Impact of model architecture on robustness and interpretability of multispectral deep learning models. In Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imaging XXIX (Vol. 12519, pp. 184-199). SPIE.
  • Godfrey, C., Kvinge, H., Bishoff, E., Mckay, M., Brown, D., Doster, T., & Byler, E. (2023). How many dimensions are required to find an adversarial example?. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 2352-2359).