I am a first year PhD student at Universidad de Zaragoza, inside Graphics and Imaging Lab. My PhD thesis is being co-supervised by Diego Gutierrez and Belen Masia. My main research topics lie in the interface between machine learning and computer graphics. In particular, I am interested in efficient light transport through learning and in the connection between perceptual cues and neural networks.
I obtained my Bachelor (2015) and Master (2016) degree at Universidad de Zaragoza, majoring in Computer Science and Applied Maths respectively. During my studies, I was an undergraduate researcher at the Graphics & Imaging Lab working on transfer learning and similarity methods.
You can contact me at mlagunas at unizar dot es
· September 2018 - Our work on Learning icons appearance similarity (part of my Master thesis) has been published at Multimedia Tools and Applications.
· July 2018 - I will attend the Deep Bayes Summer School in Moscow, this August!
· June 2018 - I have been accepted to the DS3 Data Science Summer School at the École Polytechnique in Paris!
Implementation of a U-net like model used for car segmentation in the Carvana Image Segmentation challenge run on the Kaggle platform.
Library that aims to be a high-level abstraction of three different evolutionary algorithms: Genetic Algorithms (ga), Evolution Strategies (es) and Grid-based Genetic Algorithm (gga).
Analysis of classification methods using hihgly imbalanced data acquired by the marketing team of a bank in order to predict if a client will subscribe to a particular bank deposit.
Use of penalized regression (Lasso regression) which consists on getting the correct answers of an exam given the answers of the students and their grade.