The theme "empowering communities through education" inspired me to consider how I could empower other Latinos to pursue Computer Science. Latinos are often locked out because they do not have the spare income to spend on coding courses and few Latinos are in technology to begin with (only 5% of the tech field). EasyML was inspired by my experience with Computer Science. Tools like Scratch are invaluable for learning how to code intuitively, but I noticed that nothing like it existed for Machine Learning. I sought to change that.
What it does
EasyML provides a non-intimidating environment to build Machine Learning models intuitively with no coding experience. The drag and drop interface puts the transformative of Machine Learning at everyone's fingertips regardless of their ability to code. EasyML is also complete with a walkthrough, designed for non-technical people who need an explanation of some of the Machine Learning jargon present.
How we built it
I build EasyML with a React frontend and an Express.js backend along with the mljs machine learning package.
Challenges we ran into
The main challenge I confronted was designing the drag and drop interface smoothly, and configuring the Machine Learning package to work with the API I had set up.
Accomplishments that we're proud of
I am proud of the way that the interface turned out, and truly believe that it allows even someone who has never coded before to build a powerful ML model.
What we learned
I learned a lot about how to build attractive interfaces and also how to build a machine learning model in a language other than Python.
What's next for EasyML
I see a bright future for EasyML. With a more robust walkthrough and options for more complex models, EasyML can become a tool on par with Scratch that empowers the Latino community and communities everywhere by making Machine Learning accessible.