Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Reducing Class Bias In Data-Balanced Datasets Through Hardness-Based Resampling
Pawel Pukowski, Venet Osmani
Class-bias, that is class-wise performance disparities, is typically attributed to data imbalance and addressed through frequency-based resampling. However, we demonstrate that sub…
cs.LG2024
Investigating the Impact of Hard Samples on Accuracy Reveals In-class Data Imbalance
Pawel Pukowski, Haiping Lu
In the AutoML domain, test accuracy is heralded as the quintessential metric for evaluating model efficacy, underpinning a wide array of applications from neural architecture searc…
cs.LG2023
SkelEx and BoundEx: Natural Visualization of ReLU Neural Networks
Pawel Pukowski, Haiping Lu
Despite their limited interpretability, weights and biases are still the most popular encoding of the functions learned by ReLU Neural Networks (ReLU NNs). That is why we introduce…