Gustavo A. Salazar-Gomez
I am a Mechatronics Engineer with a Postgraduate Diploma in Artificial Intelligence from Universidad Autonoma de Occidente (UAO), mainly interested in topics related to Mobile Robotics, Intelligent control systems, Artificial intelligence, Navigation, Aerospace, Computer vision, Machine learning and Deep learning.
My BEng degree project was entitled “Object recognition in images using deep learning” where I used transfer learning in order to retrain the last layers of inception-v3 neural network and created new categories from a specific environment under the supervision of Jesus Alfonso Lopez at UAO.
Currently, I’m a MSc student in Mobile, Autonomous and Robotic Systems at Grenoble INP, doing an intership at INRIA's Chroma lab.
Email: gustavo [dot] salazar [at] grenoble-inp [dot] org
Github  / 
Google Scholar  / 
Linkedin  / 
Email  / 
CV
|
|
Projects
|
|
Style-transfer for the creation of aesthetic images
Gustavo A. Salazar-Gomez,
Miguel Saavedra,
Sebastian Botero
code /
report (spanish) /
description
Style-transfer implementarion based on the paper A neural algorithm of artistic style using VGG-19.
|
|
Convolutional Nerual Network Models
Gustavo A. Salazar-Gomez
code
Convolutional Neural Network Models LeNet5 and VGG16 with Tensorflow for MNIST dataset, trained with GPU on Colab.
|
|
Classical Machine Learning
Gustavo Salazar
code
Machine Learning projects from Supervised methods like KNN, Decision Trees and ANN, and Unsupervised methods like DBSCAN and PCA, finally feature engineering to improve models performance.
|
|
Generative Adversarial Networks
Gustavo A. Salazar-Gomez
code
Generative Adversarial Networks(GAN) used to generate cars images from CIFAR10, trained with GPU on Colab.
|
|
Face recognition using LBP
Gustavo Salazar,
Nicolas Diaz
code
Face recognition using LBP features, the system extract the LBP features from the face in the image and a SVM is trained in order to classify each face. There could be multiple faces in the scene.
|
|
Sudoku recognizer with OpenCV
Gustavo Salazar
code
Sudoku recognizer using OpenCV to process the image, and a KNN as ML model to classify each digit found, finally the result is displayed in a grid where the numbers are in the same position as the image.
|
Courses and Certifications
-
Introduction to Satellite Communications by Institut Mines-Télécom on Coursera. Certificate earned on January 2, 2020. [Credential]
|
|