Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Ratko Pilipović"'
Publikováno v:
Sensors, Vol 21, Iss 12, p 4195 (2021)
Edge computing brings artificial intelligence algorithms and graphics processing units closer to data sources, making autonomy and energy-efficient processing vital for their design. Approximate computing has emerged as a popular strategy for energy-
Externí odkaz:
https://doaj.org/article/29bfbf03e2b74cfd95d8c364991d4ff4
On the Design of an Energy Efficient Digital IIR A-Weighting Filter Using Approximate Multiplication
Publikováno v:
Sensors, Vol 21, Iss 3, p 732 (2021)
This paper presents a new A-weighting filter’s design and explores the potential of using approximate multiplication for low-power digital A-weighting filter implementation. It presents a thorough analysis of the effects of approximate multiplicati
Externí odkaz:
https://doaj.org/article/c698d902215e4a228c4bfcbadf1dc268
Publikováno v:
Sensors, Vol 18, Iss 7, p 2351 (2018)
Wireless sensor networks can provide a cheap and flexible infrastructure to support the measurement of noise pollution. However, the processing of the gathered data is challenging to implement on resource-constrained nodes, because each node has its
Externí odkaz:
https://doaj.org/article/951fcd1026d647b98156a9dc3a18c18d
This paper proposes a novel approximate bfloat16 multiplier with on-the-fly adjustable accuracy for energy-efficient learning in deep neural networks. The size of the proposed multiplier is only 62% of the size of the exact bfloat16 multiplier. Furth
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::39609f1135ee5ade7c61f98ad64c2bf7
https://doi.org/10.36227/techrxiv.22123127.v1
https://doi.org/10.36227/techrxiv.22123127.v1
Autor:
Ratko Pilipovic, Patricio Bulic
Publikováno v:
IEEE Access, Vol 8, Pp 64578-64590 (2020)
This paper proposes an energy-efficient approximate multiplier which combines radix-4 Booth encoding and logarithmic product approximation. Additionally, a datapath pruning technique is proposed and studied to reduce the hardware complexity of the mu
Externí odkaz:
https://doaj.org/article/2658f4c6db2047ba82418e7c4e51193e