In this project, we explored whether ensembling transformers or increasing model size improves news source classification. Using a curated dataset of 3,713 Fox and NBC headlines, we found that transformer ensembles outperformed the best individual models by 1.08%. In contrast, scaling up from BERT-base to BERT-xlarge did not improve performance, showing that model diversity is more effective than size for short-text classification tasks.

This is a Stirling Engine modeled as a hamster running in a wheel. The engine was designed in SOLIDWORKS and most parts were machined at UPenn's Precision Machining Laboratory using, Mill, Lathe, and CNC Operations.