Semi-supervised Neural Networks solve an inverse problem for modeling Covid-19 spread, published at NeurIPS 2020 Workshop

In this work, we study the spread of COVID-19 using a semi-supervised neural network and assuming a passive part of the population remains isolated from the virus dynamics. We applied a novel method do solve differential equations with Neural Networks.

From Potential to Rays

In this research project we leveraged Deep Learning to study a well-known optics problem, namely trying to predict where caustics will emerge, given the position and the intensity of the rays hitting a surface. The architecture proposed consists of two Variational Autoencoders and a Feed-Forward...

Neural Style Transfer - Pytorch implementation

Neural Style Transfer is an optimization technique to manipulate an image and apply the visual appearance of another one. This allows creating of peculiar artworks like the followings, which I borrowed from the original paper. This repository contains the code that replicates the paper of Gatys...

Medium - Towards Data Science Writer

I regularly write Data Science and Machine Learning blog‐posts. Click on the links to read my most-read articles. (1) Using AI to automatically estimate the status of a façade (2) What I learned about Graph Neural Networks (3) Introduction to Reinforcement Learning: Temporal...