li { border: 1px solid grey; }
Hi! Hello and welcome to my website! I am Hugo!
You can find some of my blog posts here. In addition, you can check out or contribute to any of my projects by clicking here.
I am a passionate computer scientist currently working in computer vision systems. I have 2+ years of work experience as a machine learning scientist, data scientist, and software engineer. In addition, I often work with game development.
I successfully achieved my Master's degree in Machine Learning from Université Laval (Quebec) and my Bachelor's degree in Computer Science from the Federal University of Rio de Janeiro (Brazil).
Regardless of the current project, I believe that reasoning is a powerful weapon against almost any human error. If we want to keep building a great world for humanity, perhaps reasoning can be the ultimate answer. And that's why I'm always looking for data to help me solve every problem I face.
In my spare time, I enjoy philosophical discussions, listening to video game music, and learning meaningless things like typing faster.
Oct 2021 - Currently
- Implemented a computer vision pipeline (data labeling for 3D segmentation, training and evaluating model) for point cloud classification using PointCNN.
- Guided a pick and place robotic solution using Universal Robots and Realsense/Kinect/Ensenso cameras.
- Implemented a production-level QT desktop application for robotic tool.
- Technologies: Open3D, Pytorch, Universal Robots, Azure Kinect DK, Computer Vision
Apr 2021 - Oct 2021
- Implemented a hand tracking system to work in low-light conditions using numerous realsense cameras.
- Implemented a pose estimation system and OSC server in Unity Engine.
- Technologies: Computer Vision, Machine learning, Unity Engine, Realsense Camera, OSC, Python, and C#.
Nov 2017 - May 2018
- Implemented a manageable infrastructure for image processing in cloud servers, which reduced total process time by 30%.
- Automated expensive and time-consuming tasks (10TB training data for annotation) using SOTA deep learning methods.
- Presented key findings for end customers to the team leader and wrote an executive report.
- Technologies: Deep Learning, Computer Vision, AWS, Docker, and Python.
Global Research
Nov 2016 - Nov 2017
- Deployed 100+ wearable applications that gather training data and send to docker containers.
- Gathered and Wrangled 1TB data for Human Activity Recognition system that was previously inaccessible datasets.
- Improved 50% accuracy and 400% speed for predictions to end clients to track impact at real-time.
- Technologies: Deep learning, Time Series, Docker, Python, C++ and Javascript.
December 2020
Laval University
- Thesis: Meta Learning Population-Based Algorithms in Black-box Optimization
- Fellowships:
- Relevant Coursework:
- Deep Learning
- Statistical Learning
- Reinforcement Learning
- Big Data Analytics
December 2017
Federal University of Rio de Janeiro
- Thesis: Towards Deep Q-Caching
- Fellowships:
- National Council of Scientific Researches Scholarship
- Institutional Scientific Initiation Scholarship
- Teach Assistant (TA):
- Data Structures and Algorithms
- Formal Languages
2021
Meta Learning Black-Box Population-Based Optimizers
Hugo Siqueira Gomes , Benjamin Léger, Christian Gagné
The no free lunch theorem states that no model is better suited to every problem. A question that arises from this is how to design methods that propose optimizers tailored to specific problems achieving state-of-the-art performance. This paper addresses this issue by proposing the use of meta-learning ...
2019
Unsupervised Temperature Scaling: Post-Processing Unsupervised Calibration of Deep Models Decisions
Azadeh Sadat Mozafari, Hugo Siqueira Gomes , Wilson Leão, Christian Gagné
The great performances of deep learning are undeniable, with impressive results over a wide range of tasks. However, the output confidence of these models is usually not well-calibrated, which can be an issue for applications where confidence ...
