Parijat Dube

P2L: Predicting Transfer Learning for Images and Semantic Relations

2020

We describe an efficient method to accurately estimate the effectiveness of a previously trained deep learning model for use in a new learning task. We use this method, "Predict To Learn" (P2L), to predict the …

Detection of data drift and outliers affecting machine learning model performance over time

2020 · arXiv (Cornell University)

A trained ML model is deployed on another `test' dataset where target feature values (labels) are unknown. Drift is distribution change between the training and deployment data, which is concerning if model performance changes. For …