About me

Hi! My name is Javier (pronounced like ha-bee-air). I am a third year PhD Candidate in the Signal and Image Processing & Machine Learning (SIPML) track of the Electrical and Computer Engineering (ECE) department at the University of Michigan. I am co-advised by Laura Balzano and Jeffrey Fessler. I collaborate with Scott Peltier from the Biomedical Engineering (BME) department. I am fortunate to be partially supported by the Rackham Merit Fellowship. My research interests are topics such as signal/image processing, machine learning, deep learning, medical imaging, optimization, and applied math.

My research so far focuses on the following:

  • Designing machine learning algorithms to better handle heteroscedastic (noisy) data distributions such as:
    • Subspace basis estimation of low-rank data with an improved PCA-like algorithm
    • Unsupervised learning of low-rank data clusters with an improved K-Subspaces algorithm
  • Alzheimer’s disease in resting state / task-based functional MRI data with novel deep learning approaches such as:
    • 4D CNN architecture to handle raw data (X,Y,Z,T) for classifying subjects
    • Contrastive learning of structural MRI (X,Y,Z) for latent variable downstream tasks
    • Using Power atlas ROIs, learning temporal dynamics of timeseries (T, 272 regions) for classifying subjects

In the navigation bar above, I have various sections available ranging from:

  1. Publications = Publications and preprints
  2. Talks = Talks/Presentations over the years at various academic groups/conferences
  3. Teaching/Awards = Teaching experience and academic awards received over the years
  4. Industry = Industry experience and portfolio
  5. Grad Work = Graduate portfolio and projects
  6. Undergrad Work = Undergraduate portfolio and projects
  7. Certs = Certifications ranging from IT, 3D mechanical design, and more
  8. CV = A one page CV/Resume PDF