LEARNING
NeuFlow: Dataflow vision processing system-on-a-chip
Phi-Hung Pham, Darko Jelaca, Clément Farabet, Berin Martini, Yann LeCun, Eugenio Culurciello
- Year
- 2012
- Citations
- 86
Abstract
Abstract—This paper presents a bio-inspired vision systemon-a-chip- neuFlow SoC implemented in the IBM 45 nm SOI process. The neuFlow SoC was designed to accelerate neural networks and other complex vision algorithms based on large numbers of convolutions and matrix-to-matrix operations. Postlayout characterization shows that the system delivers up to 320 GOPS with an average power consumption of 0.6 W. The powerefficiency and portability of this system is ideal for embedded vision-based devices, such as driver assistance, and robotic vision. I.
Keywords
Software portabilityComputer scienceDataflowMachine visionIBMSystem on a chipEmbedded systemChipProcess (computing)Computer hardware
Related papers
OTHER
📊 26,957 cites
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
PERCEPTION
📊 22,245 cites
Artificial intelligence: a modern approach
1995
OTHER
📊 18,993 cites
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
SWARM
📊 14,853 cites
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002