4 papers
On the Estimation of Chernoff Information
Kadircan Aksoy, Peter Jung
Chernoff information is a fundamental divergence measure characterizing the optimal error exponent in Bayesian binary hypothesis testing, with applications in information fusion, t…
Implicit Hypothesis Testing and Divergence Preservation in Neural Network Representations
Kadircan Aksoy, Protim Bhattacharjee, Peter Jung
We study the training dynamics of neural classifiers through the lens of binary hypothesis testing. We re-formalize classification as a collection of binary tests between class-con…
Compressed learning based onboard semantic compression for remote sensing platforms
Protim Bhattacharjee, PEter Jung
Earth observation (EO) plays a crucial role in creating and sustaining a resilient and prosperous society that has far reaching consequences for all life and the planet itself. Rem…
Onboard Out-of-Calibration Detection of Deep Learning Models using Conformal Prediction
Protim Bhattacharjee, Peter Jung
The black box nature of deep learning models complicate their usage in critical applications such as remote sensing. Conformal prediction is a method to ensure trust in such scenar…