Stochastic Computing Systems

Gaines, Brian R.

doi:10.1007/978-1-4899-5841-9_2

Cited by 598 publications

(318 citation statements)

References 59 publications

Supporting

Mentioning

297

Contrasting

Order By: Relevance

“…There are at least three popular approaches for digital ANN -stochastic, fixed point and floating point. Stochastic digital ANN implementations encode the value of a signal using the probability of a given bit in a stochastic pulse stream being a logic 1 [8]. This has the benefit that many common arithmetic operations require very simple logic [9].…”

Section: Hardware Implementationmentioning

confidence: 99%

Towards Hardware Acceleration of Neuroevolution for Multimedia Processing Applications on Mobile Devices

Larkin

Kinane

O’Connor

2006

Neural Information Processing

View full text Add to dashboard Cite

Abstract. This paper addresses the problem of accelerating large artificial neural networks (ANN), whose topology and weights can evolve via the use of a genetic algorithm. The proposed digital hardware architecture is capable of processing any evolved network topology, whilst at the same time providing a good trade off between throughput, area and power consumption. The latter is vital for a longer battery life on mobile devices. The architecture uses multiple parallel arithmetic units in each processing element (PE). Memory partitioning and data caching are used to minimise the effects of PE pipeline stalling. A first order minimax polynomial approximation scheme, tuned via a genetic algorithm, is used for the activation function generator. Efficient arithmetic circuitry, which leverages modified Booth recoding, column compressors and carry save adders, is adopted throughout the design.

show abstract

Section: Hardware Implementationmentioning

confidence: 99%

Towards Hardware Acceleration of Neuroevolution for Multimedia Processing Applications on Mobile Devices

Larkin

Kinane

O’Connor

2006

Neural Information Processing

View full text Add to dashboard Cite

show abstract

“…Several types of PSP schemes have been proposed in various areas such as communications and controls. Stochastic computing (Gaines, 1969), (Hori et al, 2006) is one of the PSP schemes. Bernoulli sequences used in stochastic computing have uniformly distributed frequency spectra of quantization errors.…”

Section: Fig 1 Coulomb Blockade and Single-electron Tunnelingmentioning

confidence: 99%

Single-Electron Circuits for Sigma-Delta Domain Signal Processing

Fujisaka¹

2010

Cutting Edge Nanotechnology

View full text Add to dashboard Cite

“…This is our stochastic bitstream. [18,27]. Further on, if 'bitstream' is mentioned it is meant to be a stochastic bitstream.…”

Section: Definitionmentioning

confidence: 99%

Stochastic bitstream‐based CNN and its implementation on FPGA

Rák

Soós

Cserey

2008

Circuit Theory & Apps

View full text Add to dashboard Cite

SUMMARYIn this paper, we present a new type of cellular nonlinear network (CNN) model and FPGA implementation of cellular nonlinear network universal machine. Our approach uses stochastic bitstreams as data carriers. With the help of stochastic data streams more complex nonlinear cell interactions can be realized than conventional CNN hardware implementations have. The accuracy as indexed by bit depth resolution can be improved at the expense of computation time without influencing hardware complexity. Our simulation results prove the universality and utility of the model. Our experimental results show that the proposed model can be implemented on an FPGA hardware.

show abstract

Stochastic Computing Systems

Cited by 598 publications

References 59 publications

Towards Hardware Acceleration of Neuroevolution for Multimedia Processing Applications on Mobile Devices

Towards Hardware Acceleration of Neuroevolution for Multimedia Processing Applications on Mobile Devices

Single-Electron Circuits for Sigma-Delta Domain Signal Processing

Stochastic bitstream‐based CNN and its implementation on FPGA

Contact Info

Product

Resources

About