Portfolio

Background

I still remember Gamal Abdel Nasser's rise and fall as vividly as a film - not because I'm a history fan, but because of how I learned it. In fall 2021 at LSMSA, Dr. Kyle Stephens taught the modern Middle East as a line of vivid stories where historical figures were drawn out as very real people with desires and fears. It was like watching a play unfold, not sitting through a lecture. That being said. It was absolutely the most difficult class I had ever taken. But it taught me something 13 years of Louisiana public school couldn't: when you enjoy the learning process, you can learn anything. Once I saw what learning could be, I couldn't unsee what was missing everywhere else. The problem wasn't that students were lazy or incapable - it was that most education environments kill enjoyment. If I could figure out how to make a system where education was more engaging, I could change everything. That insight has driven everything I've built since. I start with a problem I or someone I know actually experiences. I build a system that recognizes what's going wrong. Then I design it to respond in a way that matters. With Aluminotes, I recognized that ADHD brains process information faster but with less clarity - and built a tool that responds by reformatting their notes. With my research on curriculum learning, I learned to recognize what neural networks struggle with - and ran experiments with metrics to learn what makes certain images complex. With Ascend, I recognized that students disengage when math feels impossibly hard or boringly easy - and built a system that adapts in real-time. My goal is to make the engagement of Dr. Stephens' classroom the norm, not the exception. To build systems that recognize struggle and respond with the kind of care that actually helps people learn.

Projects Introduction

I build systems that recognize and respond to the user. Because I know the magic of education isn't just knowledge transfer - it's when the system sees what's needed and adjusts. These projects show three different angles on that: helping ADHD students take notes and account for potential gaps, learning systems that adapt to the student's skill level, and research in understanding what makes information difficult in other systems. They all come from the same belief: good systems pay attention.

Aluminotes

Accessibility SoftwareEdTechPitch Competition Winner

The Aluminotes home page, with the logo on the right (a black paper crane against a bright red-orange gradient, the letters "Al" in a bold black to white gradient font behind it) and information about the website on the left.

My friends and I with ADHD couldn’t keep up with traditional note-taking—our notes were broken and useless by the end of lectures. So we built Aluminotes: an AI system that recognizes messy notes and transforms them into structured, reviewable summaries.

We built it on Django using Google Gemini. The system takes shorthand notes and outputs coherent lecture summaries with proper structure and context. We tested it on ourselves - being our own users let us focus on real pain points instead of guessing.

We won first place at our school’s Inn-eaux-vate pitch competition. But the real win was proving something I still believe, and that I find myself lucky to experience: EdTech works best when built by people who actually experienced the problem. Because we were the users, we knew what to solve and improve.

You can find the code at https://github.com/DudeSquaredEdud/Aluminotes

(Aluminotes.net is, sadly, now defunct)

BeNakama

Fullstack DevelopmentEdTechAccessability

A gif of the Ascend combat system, with the protagonist (a knight) on the left, an enemy (a bush monster) on the right. The combat goes through multiple question prompts.

After my undergraduate research on curriculum learning, I wanted to apply those principles at scale. I sought a position where I could implement adaptive learning systems that balance challenge and engagement - the core insight I gained from Dr. Stephens’ class. BeNakama’s mission to prioritize genuine learning over compliance metrics aligned perfectly with my philosophy.

As fullstack engineer, I work across the entire stack to build Ascend’s combat and adaptive difficulty system. I work on Ascend’s adaptive system: it watches how students perform and adjusts math problems in real-time to keep them challenged but not overwhelmed.

The RPG format keeps students engaged while the underlying algorithms ensure they’re working at their optimal challenge level. I’m involved in both the design decisions and implementation, allowing me to ensure the technical architecture serves the pedagogical goals.

Ascend represents my first professional implementation of research-backed adaptive learning. The system is designed to identify individual student strengths and weaknesses, then use that data to create personalized learning pathways. My goal is to prove that technology can scale the kind of personalized, challenging, engaging education I experienced at LSMSA to students in UK high schools and beyond.

You can sign up at https://play.benakama.com

Wavelet Analysis Research

Machine LearningUndergraduate ResearchIBM Presentation

The logo for the Deep Learning and Data Analysis Lab at The University of Louisiana, Lafayette. The logo itself is a popout effect from a wavy, purple and blue background, with the letters "D" "A" "D" "L".

The poster for the wavelet analysis research that was presented at IBM.

I wanted to understand: what makes an image hard for a neural network to classify? I used wavelet entropy as a measure of image complexity, then tested whether ordering training by difficulty improves learning. Presented at IBM’s Thomas J. Watson Laboratory.

Although I had help out in the DADL lab before, this was the first project where I was more in the know about the process than the other researchers. Wavelet complexity was brought up in a meeting after thinking about my favorite GIMP image effect, “wavelet decomposition”.

My mentor at the time, Gabriel Trahan, had experience in signal theory. He knew that wavelets were used as a means of extracting signal from noise, but had never thought about them in an image context. I knew about them from the image point of view, but never knew how they worked.

I used a math technique called wavelet entropy to measure how ‘complex’ an image is for neural networks. Initial testing showed promise, but an unnoticed grouping in the data made results worse overall. I’m still proud of this work - it taught me something crucial: simple details matter more than big theory. That lesson changed how I approach research.

I am still proud of the experiment and I even have the poster on my wall. I believe I learned a valuable lesson on how simple considerations are often lost when thinking about the big picture.