12 citations · 25 across the 12 of their papers we have counts for
13 papers
A Differentiable Approach to Combinatorial Optimization using Dataless Neural Networks
Ismail R. Alkhouri, George K. Atia, Alvaro Velasquez
The success of machine learning solutions for reasoning about discrete structures has brought attention to its adoption within combinatorial optimization algorithms. Such approache…
Protein Folding Neural Networks Are Not Robust
Sumit Kumar Jha, Arvind Ramanathan, Rickard Ewetz +2
Deep neural networks such as AlphaFold and RoseTTAFold predict remarkably accurate structures of proteins compared to other algorithmic approaches. It is known that biologically sm…
Pulmonary Disease Classification Using Globally Correlated Maximum Likelihood: an Auxiliary Attention mechanism for Convolutional Neural Networks
Edward Verenich, Tobias Martin, Alvaro Velasquez +2
Convolutional neural networks (CNN) are now being widely used for classifying and detecting pulmonary abnormalities in chest radiographs. Two complementary generalization propertie…
BOSS: Bidirectional One-Shot Synthesis of Adversarial Examples
Ismail R. Alkhouri, Alvaro Velasquez, George K. Atia
The design of additive imperceptible perturbations to the inputs of deep classifiers to maximize their misclassification rates is a central focus of adversarial machine learning. A…
Controller Synthesis for Omega-Regular and Steady-State Specifications
Alvaro Velasquez, Ismail Alkhouri, Andre Beckus +2
Given a Markov decision process (MDP) and a linear-time (-regular or LTL) specification, the controller synthesis problem aims to compute the optimal policy that satisfies the s…
Steady-State Planning in Expected Reward Multichain MDPs
George K. Atia, Andre Beckus, Ismail Alkhouri +1
The planning domain has experienced increased interest in the formal synthesis of decision-making policies. This formal synthesis typically entails finding a policy which satisfies…
Domain Wall Leaky Integrate-and-Fire Neurons with Shape-Based Configurable Activation Functions
Wesley H. Brigner, Naimul Hassan, Xuan Hu +7
Complementary metal oxide semiconductor (CMOS) devices display volatile characteristics, and are not well suited for analog applications such as neuromorphic computing. Spintronic…
An Extension of Fano's Inequality for Characterizing Model Susceptibility to Membership Inference Attacks
Sumit Kumar Jha, Susmit Jha, Rickard Ewetz +4
Deep neural networks have been shown to be vulnerable to membership inference attacks wherein the attacker aims to detect whether specific input data were used to train the model.…
Improving Explainability of Image Classification in Scenarios with Class Overlap: Application to COVID-19 and Pneumonia
Edward Verenich, Alvaro Velasquez, Nazar Khan +1
Trust in predictions made by machine learning models is increased if the model generalizes well on previously unseen samples and when inference is accompanied by cogent explanation…
Unsupervised Competitive Hardware Learning Rule for Spintronic Clustering Architecture
Alvaro Velasquez, Christopher H. Bennett, Naimul Hassan +5
We propose a hardware learning rule for unsupervised clustering within a novel spintronic computing architecture. The proposed approach leverages the three-terminal structure of do…
Plasticity-Enhanced Domain-Wall MTJ Neural Networks for Energy-Efficient Online Learning
Christopher H. Bennett, T. Patrick Xiao, Can Cui +6
Machine learning implements backpropagation via abundant training samples. We demonstrate a multi-stage learning system realized by a promising non-volatile memory device, the doma…
The Utility of Feature Reuse: Transfer Learning in Data-Starved Regimes
Rashik Shadman, M. G. Sarwar Murshed, Edward Verenich +2
The use of transfer learning with deep neural networks has increasingly become widespread for deploying well-tested computer vision systems to newer domains, especially those with…
FlexServe: Deployment of PyTorch Models as Flexible REST Endpoints
Edward Verenich, Alvaro Velasquez, M. G. Sarwar Murshed +1
The integration of artificial intelligence capabilities into modern software systems is increasingly being simplified through the use of cloud-based machine learning services and r…