Hi, I’m Oscar Guarnizo, a young computer scientist from Ecuador. My research expertise relies on computer vision and deep learning. I have already worked on projects related to convolutional neural networks (CNN) for classification, segmentation, license plate recognition, and generative adversarial networks. However, I am currently turning towards Reinforcement Learning (RL) research, a mature technology with a solid contextualization and mathematical formulation.

🌟 Skills

Technical Skills

• Machine Learning: Classification, Detection, Segmentation (using , , ), Image Generation (using ), and Decision Making (using ).

• Deep Learning: Hyperparameter Tuning, Regularization, Optimizations, Convolutional Neural Networks, Transfer Learning, Data Visualization (using and ).

• Interested: Reinforcement Learning, Graph Neural Networks, Natural Language Processing, and Data Science.

Coding Skills

🚀 Portfolio

A portfolio that grouped my recent research works about AI/ML.

Automatic License Plate Recognition (Nvidia TAO + Deepstream Application + Python Bindings)

In this work, we develop an entire process for the Automatic License Plate Recognition (ALPR) system using mainly Nvidia TAO Toolkit and Nvidia Deepstream SDK using the Python Bindings. Continue reading Automatic License Plate Recognition (Nvidia TAO + Deepstream Application + Python Bindings)

Convolutional Neural Network Feature Extraction Using Covariance Tensor Decomposition (Open Access)

This work introduces a new algorithm based on multilinear algebra for feature extraction (Covariance Tensor Decomposition), which later is plugged into a CNN to perform classification. Continue reading Convolutional Neural Network Feature Extraction Using Covariance Tensor Decomposition (Open Access)

See Portfolio for more

✨ Motivations

Some motivations about my current interests and learning in AI/ML.

Machine Learning	Mathematics	Game AI

See Motivations for more