I'm a fourth-year Computer Science student at UC San Diego with a passion for building, creating, and exploring the intersections of technology and biology. Welcome to my portfolio!
Learn More About MeMy name is Enrique, and I am currently a Fourth-Year at University of California, San Diego pursuing a Bachelor's in Computer Science and minor in General Biology. I'm passionate in Machine Learning, Cybersecurity, Computational Biology, and Software Engineering.
My passion for computer science stems from the fourth grade, where the Gifted and Talented Education (G.A.T.E.) program introduced me to coding. The programs and games I was able to make in Scratch were mindblowing to me and allowed me to express my creativity and indulge in my curiosity. This enthusiasm carried on to middle school and high school where I joined the Robotics club and became part of the software team for our robot. After acing my AP Computer Science exams, I decided I wanted to major in computer science and pursue what I love for my career. Now, with the skills I’ve practiced in university, I’m once again able to express my creativity through projects such as this website, and I anticipate learning more throughout my career.
Worked in a team of 4 to design and implement a symbolic music generation model using Recurrent Neural Networks (RNNs) trained on MIDI datasets. We extracted features such as pitch, duration, and note sequences using miditoolkit, and trained the model to predict tokenized note sequences with a language modeling objective.
Technologies: Python, PyTorch, miditoolkit, FluidSynth
View on GitHubWorked in a team of 7 to create a React web app where students can create an account and fill out a survey to receive a playlist based on their current mood. We achieved this using the Spotify API to implement a recommendation system where a certain emotion is linked to certain parameters that would return an appropriate list of songs.
Technologies: HTML, CSS, React, MongoDB, Spotify API
View on GitHubWorked in a team of 10 using machine learning methods to investigate the relationship between several classroom metrics and their effects on student success. We used deep neural networks to derive data from UCSD's Course and Professor Evaluations database and display a predictive model that would highlight certain patterns.
Technologies: Python, pandas, matplotlib, seaborn, sklearn
View on GitHubI've developed a website for my club at UCSD, a great example of my web development skills.
Visit My UCSD Club WebsiteFeel free to reach out if you have any questions or just want to connect!
Email: enriquearandajr@gmail.com