Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Mohammad Samragh"'
Streaming keyword spotting is a widely used solution for activating voice assistants. Deep Neural Networks with Hidden Markov Model (DNN-HMM) based methods have proven to be efficient and widely adopted in this space, primarily because of the ability
Externí odkaz:
http://arxiv.org/abs/2210.15425
Publikováno v:
IEEE Journal on Emerging and Selected Topics in Circuits and Systems. 11:611-619
Tensor decomposition is a promising approach for low-power and real-time application of neural networks on resource-constrained embedded devices. This paper proposes AutoRank, an end-to-end framework for customizing neural network decomposition using
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1913adefe3d8ebc2b68a247a11bfb572
https://doi.org/10.1109/jetcas.2021.3127433
https://doi.org/10.1109/jetcas.2021.3127433
Streaming keyword spotting is a widely used solution for activating voice assistants. Deep Neural Networks with Hidden Markov Model (DNN-HMM) based methods have proven to be efficient and widely adopted in this space, primarily because of the ability
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0bf80e4d2bcb5eb82f993f2522359627
http://arxiv.org/abs/2210.15425
http://arxiv.org/abs/2210.15425
Autor:
Mohammad Samragh, Arnav Kundu, Ting-Yao Hu, Aman Chadha, Ashish Srivastava, Minsik Cho, Oncel Tuzel, Devang Naik
This paper explores the possibility of using visual object detection techniques for word localization in speech data. Object detection has been thoroughly studied in the contemporary literature for visual data. Noting that an audio can be interpreted
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::23ffa89be6cdc18585cc4b9011c377db
http://arxiv.org/abs/2210.13567
http://arxiv.org/abs/2210.13567
Publikováno v:
IEEE Design & Test. 38:31-38
Editor’s note: This article describes DeepFense, a framework to make deep learning models automatically and efficiently realizable on constrained devices. — Rosario Cammarota, Intel Labs — Francesco Regazzoni, University of Amsterdam and Univer
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fd03aff49ad3c0c26329d82af130e1d0
https://doi.org/10.1109/mdat.2021.3063344
https://doi.org/10.1109/mdat.2021.3063344
Publikováno v:
IEEE Transactions on Dependable and Secure Computing. 18:736-752
Recent advances in adversarial Deep Learning (DL) have opened up a new and largely unexplored surface for malicious attacks jeopardizing the integrity of autonomous DL systems. This article introduces CuRTAIL, a novel end-to-end computing framework t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8701d70cea9dfe9c9619063ae385d99d
https://doi.org/10.1109/tdsc.2020.3024191
https://doi.org/10.1109/tdsc.2020.3024191
Publikováno v:
ACM Transactions on Embedded Computing Systems. 19:1-29
This article proposes EncoDeep, an end-to-end framework that facilitates encoding, bitwidth customization, fine-tuning, and implementation of neural networks on FPGA platforms. EncoDeep incorporates nonlinear encoding to the computation flow of neura
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eabd75b6f19fcdaa1cabcbf24d34ba5e
https://doi.org/10.1145/3391901
https://doi.org/10.1145/3391901
Publikováno v:
IEEE Journal of Selected Topics in Signal Processing. 14:750-764
This paper introduces an adaptive sampling methodology for automated compression of Deep Neural Networks (DNNs) for accelerated inference on resource-constrained platforms. Modern DNN compression techniques comprise various hyperparameters that requi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::959c12abda2f2051a18131fb35841a0d
https://doi.org/10.1109/jstsp.2020.2992384
https://doi.org/10.1109/jstsp.2020.2992384
Publikováno v:
CCS
We introduce COINN - an efficient, accurate, and scalable framework for oblivious deep neural network (DNN) inference in the two-party setting. In our system, DNN inference is performed without revealing the client's private inputs to the server or r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::766af66379a3e7fc9fcab80b13f9f1d0
https://doi.org/10.1145/3460120.3484797
https://doi.org/10.1145/3460120.3484797
Publikováno v:
Tara Javidi
Deep neural networks have been shown to be vulnerable to backdoor, or trojan, attacks where an adversary has embedded a trigger in the network at training time such that the model correctly classifies all standard inputs, but generates a targeted, in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9a9c747f85fe9dee48943244d45f8a71
http://arxiv.org/abs/2109.02836
http://arxiv.org/abs/2109.02836