Anna Hartman

My Portfolio

Physics-informed Neural Network Project

According to Medium, "Physics Informed Neural Networks (PINNs) ... use data-driven supervised neural networks to learn a [physics] model, but also using physics equations that are given to the model to encourage consistency with the known physics of the system. They have the advantage of being both data-driven to learn a model, but also able to ensure consistency with the physics, as well as being able to extrapolate accurately beyond the available data. As such, PINNs are able to generate more robust models, with less data."
I utilized the Pytorch library to create a PINN model to solve a linear elasticity problem governed by partial differential equations. The model is detailed and explained by a research poster outlining the problem set up, background, and results.
See the project here!

My personal website

I created a personal website which includes an embedded copy of my resume, a form to contact me, and a snake game. I programmed the snake game in Javascript in order to display my abilities and provide a fun activity. This project allowed me to develop my website building skills, writing skills, and design skills. Overall, I utilized Javascript, HTML, and CSS in order to build it. It is hosted on Github Pages, and is HTPPS encrypted, which means it is secure.
See the website here!

My attendance application

I created and developed application to perform different functions with sample “attendance logs”. Given an input file of raw data, it creates objects and data structures to store the data within the file, and it can perform functions to parse through the data such as checking which students are late or absent. It also includes an intuitive and aesthetically pleasing user interface which was developed with SceneBuilder. I utilized JavaFX, Java, and FXML as well. Download the application here! See the project repo here!