A High Throughput Acceleration for Hybrid Neural Networks With Efficient Resource Management on FPGA

Deep learning is the amazing technology which has promoted the development of artificial intelligence and achieved many amazing successes in intelligent fields. Convolution-based layers (CLs), fully connected layers (FLs) and recurrent layers (RLs) are three types of layers in classic neural network...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on computer-aided design of integrated circuits and systems Ročník 38; číslo 4; s. 678 - 691
Hlavní autoři:	Yin, Shouyi, Tang, Shibin, Lin, Xinhan, Ouyang, Peng, Tu, Fengbin, Liu, Leibo, Wei, Shaojun
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.04.2019 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Acceleration Accelerators Artificial intelligence Bandwidth Convolution Engines Field programmable gate arrays Field-programmable gate array (FPGA)-based accelerators hybrid neural networks (hybrid-NNs) Machine learning Mapping Neural networks Quantization (signal) resource efficient mapping Resource management State of the art
ISSN:	0278-0070, 1937-4151
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!