Zobrazeno 1 - 10
of 360
pro vyhledávání: '"Arun K. Somani"'
Publikováno v:
IEEE Access, Vol 11, Pp 106670-106687 (2023)
Quantization, effective Neural Network architecture, and efficient accelerator hardware are three important design paradigms to maximize accuracy and efficiency. Mixed Precision Quantization is a process of assigning different precision to different
Externí odkaz:
https://doaj.org/article/2495076778684d1fa1f37f0873e6a844
Publikováno v:
IEEE Access, Vol 11, Pp 25217-25236 (2023)
Neural Architecture Search (NAS), a promising and fast-moving research field, aims to automate the architectural design of Deep Neural Networks (DNNs) to achieve better performance on the given task and dataset. NAS methods have been very successful
Externí odkaz:
https://doaj.org/article/6edeaa7f13dd4788a904c381944614db
Publikováno v:
IEEE Access, Vol 10, Pp 108374-108412 (2022)
Transformer-based Deep Neural Network architectures have gained tremendous interest due to their effectiveness in various applications across Natural Language Processing (NLP) and Computer Vision (CV) domains. These models are the de facto choice in
Externí odkaz:
https://doaj.org/article/4641bf803244465bb6f59c6f5b748815
Autor:
Ravikiran Yeleswarapu, Arun K. Somani
Publikováno v:
PeerJ Computer Science, Vol 7, p e359 (2021)
As DRAM technology continues to evolve towards smaller feature sizes and increased densities, faults in DRAM subsystem are becoming more severe. Current servers mostly use CHIPKILL based schemes to tolerate up-to one/two symbol errors per DRAM beat.
Externí odkaz:
https://doaj.org/article/eaf9fdccaab749f8a9b78189ad37a948
Autor:
Pratik Mishra, Arun K. Somani
Publikováno v:
Journal of Big Data, Vol 4, Iss 1, Pp 1-42 (2017)
Abstract The performance gap between compute and storage is fairly considerable. This results in a mismatch between the application needs from storage and what storage can deliver. The full potential of storage devices cannot be harnessed till all la
Externí odkaz:
https://doaj.org/article/66bf7ef0ae634b539496aefdd7884855
Publikováno v:
Transport, Vol 33, Iss 3 (2018)
Pavements are critical man-made infrastructure systems that undergo repeated traffic and environmental loadings. Consequently, they deteriorate with time and manifest certain distresses. To ensure long-lasting performance and appropriate level of ser
Externí odkaz:
https://doaj.org/article/5a9f304beb234529b62e8d104b312865
Publikováno v:
PeerJ Computer Science, Vol 2, p e79 (2016)
Timing Speculation (TS) is a widely known method for realizing better-than-worst-case systems. Aggressive clocking, realizable by TS, enable systems to operate beyond specified safe frequency limits to effectively exploit the data dependent circuit d
Externí odkaz:
https://doaj.org/article/318cc2c4f6404170ab026c39392c9a7a
Autor:
Koray Çelik, Arun K. Somani
Publikováno v:
Journal of Electrical and Computer Engineering, Vol 2013 (2013)
This paper presents a novel indoor navigation and ranging strategy via monocular camera. By exploiting the architectural orthogonality of the indoor environments, we introduce a new method to estimate range and vehicle states from a monocular camera
Externí odkaz:
https://doaj.org/article/16f1729c41154bb0976f341a0b91f99d
Publikováno v:
ACM Computing Surveys. 55:1-36
We review the problem of automating hardware-aware architectural design process of Deep Neural Networks (DNNs). The field of Convolutional Neural Network (CNN) algorithm design has led to advancements in many fields, such as computer vision, virtual
Publikováno v:
Proceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing.