Zobrazeno 1 - 10
of 52
pro vyhledávání: '"Sek M. Chai"'
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030682378
ECCV Workshops (5)
ECCV Workshops (5)
Quantization for deep neural networks (DNN) have enabled developers to deploy models with less memory and more efficient low-power inference. However, not all DNN designs are friendly to quantization. For example, the popular Mobilenet architecture h
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6ca9c7cc2ad666f27ce3762301702eb0
https://doi.org/10.1007/978-3-030-68238-5_10
https://doi.org/10.1007/978-3-030-68238-5_10
Publikováno v:
EMC2@NeurIPS
Quantization for deep neural networks have afforded models for edge devices that use less on-board memory and enable efficient low-power inference. In this paper, we present a comparison of model-parameter driven quantization approaches that can achi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e3598bd7fca454fbc22ca5f94baf63a
https://doi.org/10.1109/emc2-nips53020.2019.00020
https://doi.org/10.1109/emc2-nips53020.2019.00020
Autor:
Ajay Divakaran, Timothy J. Shields, Mohamed R. Amer, Amir Tamrakar, Sek M. Chai, Behjat Siddiquie
Publikováno v:
International Journal of Computer Vision. 126:440-456
We propose a novel hybrid model that exploits the strength of discriminative classifiers along with the representation power of generative models. Our focus is on detecting multimodal events in time varying sequences as well as generating missing dat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c8136b1fa8dcbc313291c839d11dd58c
https://doi.org/10.1007/s11263-017-0997-7
https://doi.org/10.1007/s11263-017-0997-7
Autor:
Sek M. Chai, Senem Velipasalar
Publikováno v:
Journal of Signal Processing Systems. 93:657-657
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::72b03212f9abcca85c6a226ec6f65e7f
https://doi.org/10.1007/s11265-021-01652-4
https://doi.org/10.1007/s11265-021-01652-4
Publikováno v:
ACM Transactions on Architecture and Code Optimization. 13:1-23
Hardware Performance Counter-based (HPC) runtime checking is an effective way to identify malicious behaviors of malware and detect malicious modifications to a legitimate program’s control flow. To reduce the overhead in the monitored system which
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1dc0e35f040ee9c73b8180b3fd92763a
https://doi.org/10.1145/2857055
https://doi.org/10.1145/2857055
Complex image processing and computer vision systems often consist of a processing pipeline of functional modules. We intend to replace parts or all of a target pipeline with deep neural networks to achieve benefits such as increased accuracy or redu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3247e0b68410928cec9ee2205e109317
http://arxiv.org/abs/1811.12108
http://arxiv.org/abs/1811.12108
Publikováno v:
2018 1st Workshop on Energy Efficient Machine Learning and Cognitive Computing for Embedded Applications (EMC2).
In order to achieve high processing efficiencies, next generation computer architecture designs need an effective Artificial Intelligence (AI)-framework to learn large-scale processor interactions. In this short paper, we present Deep Temporal Models
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::674034be109b69b0c78d8ea8c4acc03e
https://doi.org/10.1109/emc2.2018.00014
https://doi.org/10.1109/emc2.2018.00014
Publikováno v:
TrustCom/BigDataSE
Controllers of security-critical cyber-physical systems, like the power grid, are a very important class of computer systems. Attacks against the control code of a power-grid system, especially zero-day attacks, can be catastrophic. Earlier detection
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7a8b850df329c82d2b2c519ac8e54e9e
Autor:
Sek M. Chai
Publikováno v:
Computer. 48:56-63
Distributed smart cameras exploit smartphone processor performance in their node communication and video metadata exchange, allowing the network to collectively reason in interpreting the scene, generating alerts, and making decisions.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ea91eb01775e8f8313738490d4e9bce0
https://doi.org/10.1109/mc.2015.105
https://doi.org/10.1109/mc.2015.105
Publikováno v:
ISCA
This paper presents a programmable and scalable digital neuromorphic architecture based on 3D high-density memory integrated with logic tier for efficient neural computing. The proposed architecture consists of clusters of processing engines, connect
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f6dd087734f719e77ad2e9f372a412d2
https://doi.org/10.1109/isca.2016.41
https://doi.org/10.1109/isca.2016.41