Javier Salazar Cavazos
Scholar

Javier Salazar Cavazos

Google Scholar ID: 4blneycAAAAJ
PhD Candidate, University of Michigan
machine learningmedical imagingdeep learningsignal processing
Citations & Impact
All-time
Citations
8
 
H-index
2
 
i10-index
0
 
Publications
5
 
Co-authors
4
list available
Resume (English only)
Research Experience
  • Designing machine learning algorithms for heteroscedastic (noisy) data distributions
  • Developed an improved PCA-like algorithm (ALPCAH) for subspace basis estimation of low-rank data
  • Proposed an improved “K-means” style algorithm (ALPCAHUS) for unsupervised clustering of low-rank data
  • Applied novel deep learning approaches to Alzheimer’s disease analysis in resting-state/task-based fMRI
  • Designed 4D CNN (ISMRM25) with spatial-temporal kernels for 4D rs-fMRI disease diagnosis
  • Studying temporal dynamics of BOLD timeseries for behavior score regression and non-healthy subgroup detection (ongoing)
  • Developed smooth optimization algorithms for global and locally low-rank regularizers (under review)