20 citations · 39 across the 15 of their papers we have counts for
15 papers
Reverse-Time Diffusion Processes for Discrete Time Linear and Nonlinear Systems with non-Gaussian Noise
Soura Dasgupta, Brian D. O. Anderson, Raghuraman Mudumbai
Generative AI relies on finding reverse time models for a discrete-time forward diffusion with non-Gaussian initial state, but uses indirect approaches as there is no theory for di…
Scale-Free Beamforming using Swarm Arrays for Remote Sensing under Interference
Bradley Hamilton, Raghu Mudumbai, Soura Dasgupta +1
We consider a swarm array of autonomous relays that seek to cooperatively forward a desired signal to a fusion center with the maximum possible fidelity while canceling out a numbe…
Trust, but Verify: Robust Image Segmentation using Deep Learning
Fahim Ahmed Zaman, Xiaodong Wu, Weiyu Xu +2
We describe a method for verifying the output of a deep neural network for medical image segmentation that is robust to several classes of random as well as worst-case perturbation…
Linear Progressive Coding for Semantic Communication using Deep Neural Networks
Eva Riherd, Raghu Mudumbai, Weiyu Xu
We propose a general method for semantic representation of images and other data using progressive coding. Semantic coding allows for specific pieces of information to be selective…
Error Correction Codes for COVID-19 Virus and Antibody Testing: Using Pooled Testing to Increase Test Reliability
Jirong Yi, Myung Cho, Xiaodong Wu +2
We consider a novel method to increase the reliability of COVID-19 virus or antibody tests by using specially designed pooled testings. Instead of testing nasal swab or blood sampl…
Derivation of Information-Theoretically Optimal Adversarial Attacks with Applications to Robust Machine Learning
Jirong Yi, Raghu Mudumbai, Weiyu Xu
We consider the theoretical problem of designing an optimal adversarial attack on a decision system that maximally degrades the achievable performance of the system as measured by…