Final project for CS5785 Applied Machine Learning - Cornell Tech taught by Serge Belongie. A full description of the task and solution for the Search Engine can be found in Final Report.
The purpose of this work is to build a large-scale image search engine that searches for images relevant to a given natural language query and return them in order of similarity. The search engine was built using different machine learning techniques (Bag of Words, Word2Vec, PCA, Kernel Ridge Regression, Cosine Similarity) and comparing their efficiency. It is coded in Python. This project consisted of a Kaggle competition to be completed to the best of our abilities within approximately a week.
We worked in a team with Antonio Mojena, Irene Peradejordi, Simran Rajpal, and Eva Esteban to complete this challenge at Cornell Tech, NYC.