8 citations · 19 across the 9 of their papers we have counts for
11 papers
Amazon SageMaker Model Parallelism: A General and Flexible Framework for Large Model Training
Can Karakus, Rahul Huilgol, Fei Wu +7
With deep learning models rapidly growing in size, systems-level solutions for large-model training are required. We present Amazon SageMaker model parallelism, a software library…
Robustness against Adversarial Attacks in Neural Networks using Incremental Dissipativity
Bernardo Aquino, Arash Rahnama, Peter Seiler +2
Adversarial examples can easily degrade the classification performance in neural networks. Empirical methods for promoting robustness to such examples have been proposed, but often…
An Adversarial Approach for Explaining the Predictions of Deep Neural Networks
Arash Rahnama, Andrew Tseng
Machine learning models have been successfully applied to a wide range of applications including computer vision, natural language processing, and speech recognition. A successful…
Robust Design of Deep Neural Networks against Adversarial Attacks based on Lyapunov Theory
Arash Rahnama, Andre T. Nguyen, Edward Raff
Deep neural networks (DNNs) are vulnerable to subtle adversarial perturbations applied to the input. These adversarial perturbations, though imperceptible, can easily mislead the D…
Connecting Lyapunov Control Theory to Adversarial Attacks
Arash Rahnama, Andre T. Nguyen, Edward Raff
Significant work is being done to develop the math and tools necessary to build provable defenses, or at least bounds, against adversarial attacks of neural networks. In this work,…
Network-based protein structural classification
Khalique Newaz, Mahboobeh Ghalehnovi, Arash Rahnama +2
Experimental determination of protein function is resource-consuming. As an alternative, computational prediction of protein function has received attention. In this context, prote…
Resilient Learning-Based Control for Synchronization of Passive Multi-Agent Systems under Attack
Arash Rahnama, Panos J. Antsaklis
In this paper, we show synchronization for a group of output passive agents that communicate with each other according to an underlying communication graph to achieve a common goal…
Encoding Multi-Resolution Brain Networks Using Unsupervised Deep Learning
Arash Rahnama, Abdullah Alchihabi, Vijay Gupta +2
The main goal of this study is to extract a set of brain networks in multiple time-resolutions to analyze the connectivity patterns among the anatomic regions for a given cognitive…
A Passivity-Based Design for Stability and Robustness in Event-Triggered Networked Control Systems with Communication Delays, Signal Quantizations and Packet Dropouts
Arash Rahnama, Meng Xia, Panos J. Antsaklis
In this report, we introduce a comprehensive design framework for Event-Triggered Networked Control Systems based on the passivity-based concept of Input Feed-Forward Output Feedba…
An Extremum-Seeking Co-Simulation Based Framework for Passivation Theory and its Application in Adaptive Cruise Control Systems
Arash Rahnama, Meng Xia, Shige Wang +1
In this report, we apply an input-output transformation passivation method, described in our previous works, to an Adaptive Cruise Control system. We analyze the system's performan…
QSR-Dissipativity and Passivity Analysis of Event-Triggered Networked Control Cyber-Physical Systems
Arash Rahnama, Meng Xia, Panos J. Antsaklis
Input feed-forward output feedback passive (IF-OFP) systems define a great number of dynamical systems. In this report, we show that dissipativity and passivity-based control combi…