Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Sotoudeh, Matthew"'
Autor:
Sotoudeh, Matthew
Modern operating systems, browsers, and office suites have become megasystems built on millions of lines of code. Their sheer size can intimidate even experienced users and programmers away from attempting to understand and modify the software runnin
Externí odkaz:
http://arxiv.org/abs/2210.09460
Autor:
Yuan, Gina, Sotoudeh, Matthew, Zhang, David, Welzl, Michael, Mazières, David, Winstein, Keith
Publikováno v:
Yuan, Gina Sotoudeh, Matthew Zhang, David Welzl, Michael Mazières, David Winstein, Keith . Sidekick: In-Network Assistance for Secure End-to-End Transport Protocols. 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 2024 USENIX - The Advanced Computing Systems Association
Externí odkaz:
http://hdl.handle.net/10852/113711
Autor:
Sotoudeh, Matthew, Thakur, Aditya V.
Deep Neural Networks (DNNs) have grown in popularity over the past decade and are now being used in safety-critical domains such as aircraft collision avoidance. This has motivated a large number of techniques for finding unsafe behavior in DNNs. In
Externí odkaz:
http://arxiv.org/abs/2104.04413
Autor:
Sotoudeh, Matthew, Thakur, Aditya V.
Deep Neural Networks (DNNs) are rapidly gaining popularity in a variety of important domains. Formally, DNNs are complicated vector-valued functions which come in a variety of sizes and applications. Unfortunately, modern DNNs have been shown to be v
Externí odkaz:
http://arxiv.org/abs/2101.03263
Autor:
Sotoudeh, Matthew, Thakur, Aditya V.
An analogy is an identification of structural similarities and correspondences between two objects. Computational models of analogy making have been studied extensively in the field of cognitive science to better understand high-level human cognition
Externí odkaz:
http://arxiv.org/abs/2009.06592
Autor:
Sotoudeh, Matthew, Thakur, Aditya V.
Deep Neural Networks (DNNs) are rapidly being applied to safety-critical domains such as drone and airplane control, motivating techniques for verifying the safety of their behavior. Unfortunately, DNN verification is NP-hard, with current algorithms
Externí odkaz:
http://arxiv.org/abs/2009.05660
Autor:
Sotoudeh, Matthew, Thakur, Aditya V.
Analysis and manipulation of trained neural networks is a challenging and important problem. We propose a symbolic representation for piecewise-linear neural networks and discuss its efficient computation. With this representation, one can translate
Externí odkaz:
http://arxiv.org/abs/1908.06223
Autor:
Sotoudeh, Matthew, Thakur, Aditya V.
A linear restriction of a function is the same function with its domain restricted to points on a given line. This paper addresses the problem of computing a succinct representation for a linear restriction of a piecewise-linear neural network. This
Externí odkaz:
http://arxiv.org/abs/1908.06214
Autor:
Sotoudeh, Matthew, Venkat, Anand, Anderson, Michael, Georganas, Evangelos, Heinecke, Alexander, Knight, Jason
Domain specific accelerators present new challenges and opportunities for code generation onto novel instruction sets, communication fabrics, and memory architectures. In this paper we introduce an intermediate representation (IR) which enables both
Externí odkaz:
http://arxiv.org/abs/1810.09958
Autor:
Sotoudeh, Matthew, Baghsorkhi, Sara S.
As the industry deploys increasingly large and complex neural networks to mobile devices, more pressure is put on the memory and compute resources of those devices. Deep compression, or compression of deep neural network weight matrices, is a techniq
Externí odkaz:
http://arxiv.org/abs/1802.06944