About Ayesha Gonzales de Spanfelner, Ph.D.

Hi, I'm Ayesha, and I recently earned my Ph.D. in Physics from Case Western Reserve University. My research focused on how ideas from statistical mechanics—like stochastic processes and high-dimensional systems—can help us understand complex, data-driven problems in biophysics and beyond.

I'm especially interested in how these theoretical tools connect to modern machine learning, from the behavior of neural networks to the analysis of messy, real-world data.

Outside of work, I’ve performed with The Cleveland Orchestra at Carnegie Hall, run a couple of 5Ks, played in multiple soccer leagues, adopted two pets, and finished three Dungeons & Dragons campaigns.

Research areas

  • design icon

    Machine Learning in Biological Imaging

    Applied machine learning techniques to extract meaningful insights on cell adhesion behavior from time-lapse microscopy data.

  • Web development icon

    Exploratory Data Analysis

    Analyzed over 2 billion insurance claims to uncover statistical patterns and engineered features relevant to fraud detection.

  • mobile app icon

    Chatbot-Driven Knowledge Retrieval

    Designed a chatbot that translates user questions into precise answers drawn from a structured knowledge graph.

  • camera icon

    When Neural Networks Aren't Sure

    Compared algorithms that measure prediction uncertainty in neural networks to detect when new or unseen object classes appear.

Résumé

Experience

  1. Data Science Intern, Noblis

    June 2023 — February 2024

    Developed a semantic search tool that maps natural language questions to structured paths on a knowledge graph to retrieve accurate organizational data. Tackled challenges in internal language and acronym ambiguity using vector databases and language models. Contributed to digital transformation efforts for CMS workflows through chatbot-driven knowledge access.

  2. Data Science Intern, Noblis

    May 2022 — August 2022

    Analyzed over 2 billion Medicare and Medicaid claims to engineer features for a fraud detection algorithm. Designed and evaluated detection models in a secure cloud computing environment, adhering to strict data privacy protocols. Collaborated with IRS-affiliated researchers to compare methodologies and insights across federal fraud investigations.

  3. Research Assistant, Case Western Reserve University

    May 2020 — September 2024

    Designed machine learning algorithms to analyze time-lapse microscopy data, focusing on cell adhesion and blood flow dynamics. Utilized high-performance computing for large-scale data processing and neural network visualization. Engaged in theoretical and applied research at the intersection of statistical mechanics and machine learning; published in peer-reviewed journals.

  4. Deep Learning Research Intern, Rochester Institute of Technology

    May 2018 — August 2018

    Implemented deep neural networks for machine learning Developed testing framework to compare various open-set algorithms in deep neural networks

Education

  1. Case Western Reserve University, 2024

    Doctor of Philosophy, Physics

    Dissertation Title: Biophysics Through the Lens of Machine Learning: Theory and Applications. Awarded NSF Graduate Research Fellowship for support of a research-based doctoral degree at an accredited institution.

  2. St. Edward's University, 2019

    Bachelor of Science, Mathematics, Physics Minor

    Dean's list, McKemie Scholar, College Assistant Migrant Program Scholar

Top skills

  • Python:

    6 years experience

  • Machine Learning:

    6 years experience

  • Natural Language Processing:

    2 years experience

  • Cloud Computing:

    4 years experience

Publications

3. Goreke, U., Gonzales, A., Shipley, B., Man, Y., Wulftange, W., An, R., Hinczewski, M., & Gurkan, U. A. (Under Revision for Nature Communications). Motion Blur Microscopy. bioRxiv Preprint.

2. Praljak, N., Shipley, B., Gonzales, A., Goreke, U., Iram, S., Singh, G., Hill, A., Gurkan, U.A. & Hinczewski, M. (2020). A Deep Learning Framework for Sickle Cell Disease Microfluidic Biomarker Assays. Blood, 136, pp.15-16. DOI,PDF.

1. Roady, R., Hayes, T. L., Kemker, R., Gonzales, A., & Kanan, C. (2020). Are open set classification methods effective on large-scale datasets?. Plos one, 15(9), e0238302. DOI,PDF.