Zobrazeno 1 - 10
of 43
pro vyhledávání: '"Rahnama, Arash"'
Adversarial examples can easily degrade the classification performance in neural networks. Empirical methods for promoting robustness to such examples have been proposed, but often lack both analytical insights and formal guarantees. Recently, some r
Externí odkaz:
http://arxiv.org/abs/2111.12906
Autor:
Karakus, Can, Huilgol, Rahul, Wu, Fei, Subramanian, Anirudh, Daniel, Cade, Cavdar, Derya, Xu, Teng, Chen, Haohan, Rahnama, Arash, Quintela, Luis
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 that integrates with PyTorch, and enables easy training of large model
Externí odkaz:
http://arxiv.org/abs/2111.05972
Autor:
Rahnama, Arash, Tseng, Andrew
Machine learning models have been successfully applied to a wide range of applications including computer vision, natural language processing, and speech recognition. A successful implementation of these models however, usually relies on deep neural
Externí odkaz:
http://arxiv.org/abs/2005.10284
Deep neural networks (DNNs) are vulnerable to subtle adversarial perturbations applied to the input. These adversarial perturbations, though imperceptible, can easily mislead the DNN. In this work, we take a control theoretic approach to the problem
Externí odkaz:
http://arxiv.org/abs/1911.04636
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, we argue that tools from control theory could be leveraged to aid in
Externí odkaz:
http://arxiv.org/abs/1907.07732
Autor:
Newaz, Khalique, Ghalehnovi, Mahboobeh, Rahnama, Arash, Antsaklis, Panos J., Milenkovic, Tijana
Experimental determination of protein function is resource-consuming. As an alternative, computational prediction of protein function has received attention. In this context, protein structural classification (PSC) can help, by allowing for determini
Externí odkaz:
http://arxiv.org/abs/1804.04725
Autor:
Rahnama, Arash, Antsaklis, Panos J.
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. We propose a distributed event-triggered control framework that will
Externí odkaz:
http://arxiv.org/abs/1709.10142
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 task. We suggest a deep architecture which learns the natural groupin
Externí odkaz:
http://arxiv.org/abs/1708.04232
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 Feedback Passive (IF-OFP) systems. Our approach is comprehensive in the sens
Externí odkaz:
http://arxiv.org/abs/1704.00592
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 performance under a co-simulation framework that makes use of an online optimiz
Externí odkaz:
http://arxiv.org/abs/1607.03958