Publications | Dr. Brian Jalaian's Website

From: To:

Featured Publications

URSABench: A System for Comprehensive Benchmarking of Bayesian Deep Neural Network Models and Inference Methods

Uncertainty Quantification

URSABench: A System for Comprehensive Benchmarking of Bayesian Deep Neural Network Models and Inference Methods

URSABench is an open-source benchmarking suite for assessing Bayesian deep learning models and inference methods, focusing on uncertainty quantification, robustness, scalability, and accuracy in classification tasks for both server and edge GPUs.

Apr 1, 2022

Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splitting

Uncertainty Quantification

Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splitting

We introduce a new symmetric integration scheme for split Hamiltonian Monte Carlo (HMC) that enables efficient inference for Bayesian neural networks on large datasets. Our method outperforms stochastic gradient MCMC in accuracy and uncertainty quantification, demonstrating HMC as a viable option for large-scale machine learning problems.

Dec 1, 2021

🔬 Selected Publications by Research Area

Recent Publications

Alice Bizzarri, Chung-en Yu, Brian Jalaian, Fabrizio Riguzzi, Nathaniel D. Bastian (2024). A Synergistic Approach In Network Intrusion Detection By Neurosymbolic AI. arXiv.

Brian Jalaian, Nathaniel D. Bastian (2023). Neurosymbolic AI in Cybersecurity: Bridging Pattern Recognition and Symbolic Reasoning. IEEE MILCOM 2023.

Vyacheslav Kungurtsev, Adam Cobb, Tara Javidi, Brian Jalaian (2023). Decentralized Bayesian learning with Metropolis-adjusted Hamiltonian Monte Carlo. Machine Learning.

Leonardo Teixeira, Brian Jalaian, Bruno Ribeiro (2023). Reducing classifier overconfidence against adversaries through graph algorithms. Machine Learning.

Nilantha Premakumara, Brian Jalaian, Niranjan Suri, Hooman SAMANI (2023). Improving Object Detection Robustness against Natural Perturbations through Synthetic Data Augmentation. Proceedings of the 2023 Asia Conference on Computer Vision, Image Processing and Pattern Recognition.