Victor Faraggi

M.Sc. in Computer Science

Identifying the reasons behind pruning's effects on generalization through data corruption, model calibration and general robustness.
My thesis encompasses the use of different state-of-the-art pruning methods applied mainly to vision architectures. Moreover, I empirically study how pruned networks approach theoretical bounds in controlled settings and how they compare with their dense counterparts.
Funded by the Millennium Institute Foundational Research on Data Science (IMFD) and National Center Artificial Intelligence (CENIA).
Department of Computer Science, Universidad de Chile Santiago, Chile

Computer Science Engineering

Department of Computer Science, Universidad de Chile Santiago, Chile

Computer Science Exchange Student

Faculty of Arts & Sciences, University of Toronto Toronto, Canada

B.Sc. in Computer Science

Faculty of Physical & Mathematical Sciences, Universidad de Chile Santiago, Chile

Machine Learning External Expert

Built the first proof-of-concept demo that generated automated reports using LLMs (closed and open-source) for a major mining company. Data varied from administrative, legal and operational documents.
PSINET Santiago, Chile

Machine Learning Engineer Intern

Studied the feasibility of using embeddings that came from different protein language models to predict protein stability. My work provided baseline results against which the team will be able to benchmark future models.
Protera Santiago, Chile

Teaching Assistant

Courses: Deep Learning, Data Mining, Algorithm Design and Analysis, Machine Learning (Mathematical Eng. Dept.), Computing Tools for Engineering, Experimental Methods (Physics Dept.), Programming I
Faculty of Physical & Mathematical Sciences, Universidad de Chile Santiago, Chile

IT Director

Organized a four man team that was tasked with maintaining and developing different technological resources of 50+ members. Coordinated the work of my team with the ongoing needs of the whole organization.
Redes Beauchef, Student Organization Santiago, Chile

Data Engineer

Analyzed satellite, oceanographic and industrial data in order to detect, prevent harmful algal blooms. With this data, built a recommendation systems to for mining companies to prevent environmental problems with desalination plants.
BloomAlert, Startup Santiago, Chile

Data Science Intern

Built a dashboard that presented analytics for the HR team of a major telecom in South America. Connected more than 10 different data-sources.
Worldalytics, Analytics & Data ScienceSantiago, Chile

Understanding Encoder-Decoder Structures in Machine Learning Using Information Measures [Submitted and in Review]

Linked information-theoretical concepts to understand effects of encoder-decoder structures in ML architectures. We provided insights into their benefits by decomposing by decomposing their effects in Cross-Entropy Learning in terms of informational measures.
I specifically led the efforts into empirically proving the theoretical results.
 U. Chile

Improving Deep Learning Prediction of Cyclone Wind Speeds with Neural ODEs

Applied Neural ODEs to model the Gradient Wind Balance equation, which is used to estimate wind speeds in tropical cyclones.
Victor Faraggi, Gary Tom, Selden Lin  U. Toronto

Investigating Climate Downscaling with Generative Super Resolution methods

Worked on the application of generative models to downscaling problems in climate science. We performed an overview of the differences between different models. In particular, we studied the difficulties in training and the transferability of established super-resolution models.
Victor Faraggi, Dhananjay Ashok, Aparna Gopalakrishnan  U. Toronto

ProjectX 2020: Machine Learning Research Competition: Climate Change

Represented U.Chile in a three-month-long ML research competition, hosted by U.Toronto. The focus of our research went into studying and developing models that could be used for landslide's early warning systems. I particularly worked on data processing and model development. Mentored by three professors: Felipe Tobar (U.Chile), Jorge Perez (U.Chile) and Apurva Narayan(U. Vancouver)
Victor Faraggi, Tomas Rojas, Jose Diaz, Francisco Munoz, Kevin Pinochet, Fabian Lema  Remote

WiFI Hacking Workshop [Presentation]

Attacks on WPS, WEP, WPA/2 and how to mitigate them. Chosen from around 100 submissions.
Victor Faraggi, Philippe Delteil, Ilana Mergudich  Defcon 27, Las Vegas