AI Research Intern

Microsoft Research

Research on models generalization, human-machine collaboration, transfer learning, and land cover mapping advised by Nebojsa Jojic and Dan Morris

Visiting Research Assistant

Mila

Research on models generalization, variational inference, and remote sensing for social good applications under Prof. Yoshua Bengio

Ph.D. Research Associate

Intelligent Agents and Strategic Reasoning Laboratory (IASRL)

Developed a deep learning architecture which jointly integrates learning and band subset selection for multispectral and hyperspectral imagery improving segmentation performance by more than 12%. Developed attacks and defenses against non-RGB image-based machine learning systems. Proposed a novel defense to increase robustness on non-RGB image-based classifiers while improving performance. Papers accepted to CVPRW 2018 and MILCOM 2018.

Visiting Research Assistant

US Army Research Laboratory (ARL-West) || USC Institute for Creative Technologies (USC-ICT)

Applied research and development in machine learning with state estimation and sensor modeling.

Visiting Research Assistant

US Army Research Laboratory (ARL-West) || USC Institute for Creative Technologies (USC-ICT)

We focused on the problem of automatically fusing hyperspectral data of a digitized scene with an image-based 3D model, overlapping the same scene, in order to associate material spectra with corresponding height information for improved scene understanding. The datasets are assumed to have been independently collected at different spatial resolutions by different aerial platforms, and the georegistration information about the datasets is insufficient, or unavailable.

Research Assistant

Vision and Learning Laboratory

Research in the areas of computer vision, and machine learning. Lead a team that developed algorithms to automatically detect and classify species of tunas, sharks and more that fishing boats catch for "The Nature Conservancy Fisheries Monitoring" kaggle competition. Other projects include using sparse modeling for multispectral video denoising and video skin detection throught hyperspectral video processing. I am currently working to improve scene understanding through the integration of deep learning, hyperspectral images, and computer vision

Teaching Assistant

Computer Science Department, UTEP

• Taught Elementary Data Structures Laboratory (4 sessions). Spring 2016, Fall 2016, Spring 2017

• Taught Introduction to Computer Science Laboratory (3 sessions). Fall 2015

Software Engineer

Advansys, SRL

Member of a team in charge of the complete redesign and development of the main software that this company sells. We used n-layer architecture, C# in the backend, WPF for the desktop version, and both SQL Server and Oracle for Databases management.

Research Assistant

Programa de Investigación en Electrónica Aplicada y Sistemas Inteligentes, PIELASI

Designed and developed an algorithm that provides visual identification about whether a geographical area contains specific mineral deposits within a target zone. First algorithm that use Landsat 8 multispectral images to identify gold using remote sensing and machine learning techniques. Developed using Matlab.

Teaching Assistant

Pontificia Universidad Católica Madre y Maestra, PUCMM

Taught Math and Physics classes.