Deep Bayesian

Deep Bayesian methods aim to address the limitations of standard deep learning by incorporating probabilistic uncertainty quantification into model predictions. Current research focuses on improving variational inference techniques, exploring alternative model architectures like deep Gaussian processes and Wishart processes, and developing efficient algorithms such as Hamiltonian Monte Carlo for posterior estimation. This work is significant because it enhances the reliability and trustworthiness of deep learning models, particularly in critical applications like medical image analysis and robotics, where understanding and managing uncertainty is paramount.

Papers

March 4, 2024

Bayesian Uncertainty Estimation by Hamiltonian Monte Carlo: Applications to Cardiac MRI Segmentation
Yidong Zhao, Joao Tourais, Iain Pierce, Christian Nitsche, Thomas A. Treibel, Sebastian Weingärtner, Artur M. Schweidtmann, Qian Tao
Financial Application Medical Image Segmentation Task Hamiltonian Monte Carlo Bayesian Uncertainty Segmentation Uncertainty Deep Learning Based Medical Bayesian Deep Deep Bayesian

January 23, 2024

Towards Improved Variational Inference for Deep Bayesian Models
Sebastian W. Ober
Gaussian Process Variational Inference Posterior Inference Variational Posterior Deep Gaussian Process Deep Bayesian

July 12, 2023

Function-Space Regularization for Deep Bayesian Classification
Jihao Andreas Lin, Joe Watson, Pascal Klink, Jan Peters
Bayesian Deep Learning Posterior Distribution Deep Bayesian Function Space Variational Inference Space Regularization

May 23, 2023

An Improved Variational Approximate Posterior for the Deep Wishart Process
Sebastian Ober, Ben Anson, Edward Milsom, Laurence Aitchison
Deep Gaussian Process Deep Bayesian

May 17, 2023

Sparsity-depth Tradeoff in Infinitely Wide Deep Neural Networks
Chanwoo Chun, Daniel D. Lee
Sparse Network Wide Neural Network Sparse Activation Neural Network Gaussian Process Deep Bayesian

February 22, 2022

Bag Graph: Multiple Instance Learning using Bayesian Graph Neural Networks
Soumyasundar Pal, Antonios Valkanas, Florence Regol, Mark Coates
Graph Neural Network Multiple Instance Learning End to End Learning Bag Level Concept Graph Deep Bayesian

December 14, 2021

Calibrated and Sharp Uncertainties in Deep Learning via Density Estimation
Volodymyr Kuleshov, Shachi Deshpande
Deep Learning Density Estimation High Uncertainty Value Distribution Calibration Global Calibration Maximum Likelihood Training Deep Bayesian

November 13, 2021

MC-CIM: Compute-in-Memory with Monte-Carlo Dropouts for Bayesian Edge Intelligence
Priyesh Shukla, Shamma Nasrin, Nastaran Darabi, Wilfred Gomes, Amit Ranjan Trivedi
Bayesian Inference Edge Intelligence Computing in Memory Dropout Method Deep Bayesian

November 10, 2021

Robust Learning via Ensemble Density Propagation in Deep Neural Networks
Giuseppina Carannante, Dimah Dera, Ghulam Rasool, Nidhal C. Bouaynaya, Lyudmila Mihaylova
Deep Neural Network Variational Inference Robust Learning Adversarial Environment Variational Distribution Deep Bayesian