Filtering by
- All Subjects: Machine Learning
- All Subjects: Technology
- Creators: Barrett, The Honors College
- Creators: Turaga, Pavan
- Status: Published
The purpose of this project is to create a useful tool for musicians that utilizes the harmonic content of their playing to recommend new, relevant chords to play. This is done by training various Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs) on the lead sheets of 100 different jazz standards. A total of 200 unique datasets were produced and tested, resulting in the prediction of nearly 51 million chords. A note-prediction accuracy of 82.1% and a chord-prediction accuracy of 34.5% were achieved across all datasets. Methods of data representation that were rooted in valid music theory frameworks were found to increase the efficacy of harmonic prediction by up to 6%. Optimal LSTM input sizes were also determined for each method of data representation.
This project did a deep dive on AI, business applications for AI and then my team and I built an AI model to better understand shipping patterns and inefficiencies of different porting regions.
This study analyzed currently existing statute at the state, federal, and international level to ultimately build a criteria of recommendations for policymakers to consider when building regulations for facial recognition technology usage by law enforcement agencies within the United States.
In this paper, I introduce the fake news problem and detail how it has been exacerbated<br/>through social media. I explore current practices for fake news detection using natural language<br/>processing and current benchmarks in ranking the efficacy of various language models. Using a<br/>Twitter-specific benchmark, I attempt to reproduce the scores of six language models<br/>demonstrating their effectiveness in seven tweet classification tasks. I explain the successes and<br/>challenges in reproducing these results and provide analysis for the future implications of fake<br/>news research.
Esports is the fastest growing sub sector within the entertainment industry, predicted to garner over 600 million viewers by 2022. However, there is a big category of esports - mobile esports - that are not yet recognized globally. This thesis project analyzes how mobile esports has risen in the Eastern countries of the world, primarily Southeast Asia, and compares it to the possibility of replication in the Western countries of the world, primarily the United States and Brazil. It examines the specific factors that caused mobile gaming and thus mobile esports to flourish in the East Region of the world. The thesis additionally incorporates current attitudes towards esports and mobile esports in the United States and discusses the viewpoints of consumers in those specific areas. This research uses primary data and literature synthesis to ultimately increase knowledge on how mobile esports has risen in popularity in various Asian countries and whether or not mobile esports can thrive in a different environment such as the United States.<br/><br/>This thesis takes data from the “Newzoo Global Esports Market Report” conducted in 2020 by Newzoo. This report does the following:<br/>- dives deep into the global and regional esports economy<br/>- provides a realistic estimate of the market’s future potential regarding revenue streams, audience numbers, key trends, and franchises<br/>- highlights financial and statistical trends for the esports industry in the future<br/><br/>Overall the thesis finds that mobile esports have succeeded in the Asian market due to an established demographic of esports fans and players, mobile first consumers, and wide technology network in Asia. Data analysis finds that currently many American gamers still find mobile gaming to be “boring” and ultimately that cultural attitude, generational shifts, and the ideal game need to align for mobile esports to succeed in the United States.