top of page

Select Projects

Vinci

Application that determines user intent and entities in order to perform everyday tasks for the user. Includes a Convolutional Neural Network that detects human facial emotion and has a conversation with you. Utilizes object detection and semantic segmentation.

Python

Tensorflow

LangChain

ChatGPT API

Bot-hoven

A deep learning architecture that generates solo piano music in the style of Ludwig van Beethoven's works. Trained on two datasets: one comprising Beethoven's 32 Piano Sonatas and other solo piano works as well as Magenta's MAESTRO dataset that includes 200 hours of piano performances. 

Python

Tensorflow

Sample composed piece:
Sonata in A minor (exposition)Bot-hoven
00:00 / 03:08

HouseBot

End-to-end framework for a robot designed to tidy a house. Incorporates a Convolutional Neural Network (CNN), Region Proposal Network (RPN), and additional feature mapping to detect objects in a room scene. The object labels are fed into ConceptNet that maps a list of verbs as the actions the robot should perform on a specified object to the object noun. Trained on scraped AI2-THOR room scenes.

Python

Tensorflow

Espressa

An original "Coffeebook"

Design

Espressa 9 x 12 FINAL.png
ESPRESSA FINAL (most up to date) (2).png
Espressa 9 x 12 FINAL (2).png
Espressa 9 x 12 FINAL (3).png
Espressa 9 x 12 FINAL (4).png
ESPRESSA FINAL (most up to date).png

La Sfogliatella

A story of the beloved Neapolitan pastry.

Design

1I0A5786.jpg
1I0A5644.jpg

Virtual Rosetta

Virtual reality environment named "The Virtual Rosetta," developed in Unity. Ancient Vietnamese drawings were organized according to a hierarchical clustering with BERT embeddings. Evaluated the effectiveness of several user interface designs before implementing the final design. Workshop paper published and presented at the 6th IEEE VIS4DH Conference on October 24, 2021.

Python

Unity

Scikit-Learn

Count BOTula

Adversarial search algorithm with a Voronoi + Dijkstra heuristic to compete against other bots in the game of Tron. Generated dataset comprised of board game configurations and corresponding winners of existing bots. Trained a supervised regression model that predicts the probability a player will win the game based on a given board game configuration.

Python

Tensorflow

Model Selection

Binary logistic regression model with Tikhonov regularization used to classify a cell as malignant or benign. Trained on the UCI Breast Cancer Wisconsin (Diagnostic) dataset.

Python

Pastry

A menu of favorite desserts I have made.

Design

Pastry Menu.png

© 2025 by Anessa Petteruti

bottom of page