Predicting Airline Delays at Scale with Spark ML

A UC Berkeley team used Apache Spark ML to predict airline delays at scale, training models on millions of flight records and ...
IEEE

Optimizing ResNet-50 for Multiclass Classification: A Multi-Stage Learning Approach

Abstract: In this study, we present a multistage learning pipeline that utilizes the ResNet-50 architecture as a static feature extractor for multiclass image classification problems. This methodology ...
IEEE

Adversarial Training and Contrastive Loss: Addressing Biases in Non-Topical Classification and Text Regression Tasks

Abstract: Topical shifts—differences between the topic distribution in training and test data—can substantially reduce the performance of non-topical text classification and regression models. In this ...