Andres studied physics at the National Autonomous University of Mexico, where he is currently studying computer science as a second major. His undergraduate thesis in physics focused on energy optimization of supported metal clusters via computer simulation. He expects to expand this work in the future by incorporating machine learning techniques for optimal cluster prediction. Andres has experience in education as a teacher assistant, teaching C programming to first- and forth-year physics undergraduates. Recently, he started working as a data scientist for a small firm in Mexico City, where he has gained interest in finance, data analysis and portfolio optimization.
In the future, Andres plans to continue his studies in interdisciplinary fields such as quantum computing, computational finance or data science.
In his spare time, he enjoys playing the piano and reading, and whenever he has the opportunity, he greatly enjoys traveling.
Project: Reverse Dictionary
Goal of the project:
Develop a system that, given a definition or description, returns the name of the corresponding concept.
Summary of work:
Nowadays, one of the main and most popular approaches to consider when dealing with large amounts of data and means to learn from it is machine learning. In the present project, this technique was explored via the built-in Wolfram Language function Classify.
Results and future work:
Classify performed well for training sets consisting of balanced word-definition pairs, that is, sets having a homologous number of definitions per word. In unbalanced sets, performance was reduced dramatically, as the classifier chose only among the most frequent words. Further improvements include finding more sources so that balancing does not represent data loss, as well as building a recurrent neural network, which has been proven to be useful for this problem.