← Search

Nicholas Konz

2 accepted papers

2024

The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images

ICLR 2024poster

This paper investigates discrepancies in how neural networks learn from different imaging domains, which are commonly overlooked when adopting computer vision techniques from the domain of natural images to other specialized domains such as medical images. Recent works have found that the generaliza…

2023

Understanding the Inner-workings of Language Models Through Representation Dissimilarity

EMNLP 2023short main

As language models are applied to an increasing number of real-world applications, understanding their inner workings has become an important issue in model trust, interpretability, and transparency. In this work we show that representation dissimilarity measures, which are functions that measure t…

Cited by 0SourceScholar