Machine learning and data science applications

The objective of this project is to develop applications of machine learning techniques and data science to problems in industrial engineering, logistics and transportation.

This project is still at an early stage. Currently, the main techniques studied have been neural networks, including convolutional neural networks for image classification, and its use in reinforcement learning.

The integration of the two technologies gives rise to deep reinforcement learning, in which an agent must make decisions based on the images it observes. This technique has been used successfully, as a proof of concept, in electronic games.

The main technologies used are the Python modules Keras and Google Tensorflow .

This project has the support of NVidia , by means of its GPU Academic Grant Program.