Current-Mode Computation with Noise in a Scalable and Programmable Probabilistic Neural VLSI System

Lu, Chih‐Cheng; Chen, H.

doi:10.1007/978-3-642-04274-4_42

Cited by 6 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A special case of stochastic neural networks, Boltzmann machines, have also been popular in neuromorphic systems. The general Boltzmann machine was utilized in neuromorphic systems primarily in the early 1990's [12], [1193]- [1199], but it has seen occasional implementations in more recent publications [1200]- [1203]. A more common use of the Boltzmann model is the restricted Boltzmann machine, because the training time is significantly reduced when compared with a general Boltzmann machine.…”

Section: Network Modelsmentioning

confidence: 99%

A Survey of Neuromorphic Computing and Neural Networks in Hardware

Schuman¹,

Potok²,

Patton³

et al. 2017

Preprint

175

180

View full text Add to dashboard Cite

Neuromorphic computing has come to refer to a variety of brain-inspired computers, devices, and models that contrast the pervasive von Neumann computer architecture. This biologically inspired approach has created highly connected synthetic neurons and synapses that can be used to model neuroscience theories as well as solve challenging machine learning problems. The promise of the technology is to create a brainlike ability to learn and adapt, but the technical challenges are significant, starting with an accurate neuroscience model of how the brain works, to finding materials and engineering breakthroughs to build devices to support these models, to creating a programming framework so the systems can learn, to creating applications with brain-like capabilities. In this work, we provide a comprehensive survey of the research and motivations for neuromorphic computing over its history. We begin with a 35-year review of the motivations and drivers of neuromorphic computing, then look at the major research areas of the field, which we define as neuro-inspired models, algorithms and learning approaches, hardware and devices, supporting systems, and finally applications. We conclude with a broad discussion on the major research topics that need to be addressed in the coming years to see the promise of neuromorphic computing fulfilled. The goals of this work are to provide an exhaustive review of the research conducted in neuromorphic computing since the inception of the term, and to motivate further work by illuminating gaps in the field where new research is needed.

show abstract

Section: Network Modelsmentioning

confidence: 99%

A Survey of Neuromorphic Computing and Neural Networks in Hardware

Schuman¹,

Potok²,

Patton³

et al. 2017

Preprint

175

180

View full text Add to dashboard Cite

show abstract

“…If we design I 7 = 2I 5 , I 8 = I 6 , I 9 = 11 8 I 1 and I 10 = 11 8 I 2 using current mirrors, and use a current sink I const = 7 8 I 0 , I out becomes…”

Section: Exponential Circuit Designmentioning

confidence: 99%

“…CMOS current-mode circuits have some advantages, such as high bandwidth, low voltage swing, and low parasitic capacitance effects. Therefore, they can be widely used in circuit design in various fields such as signal generation circuits [1][2][3], variable gain amplifiers [4,5], fuzzy function circuits [6], and neural network circuits [7]. These applications are expected to have a wide input range.…”

Section: Introductionmentioning

confidence: 99%

Design of a range-segmented CMOS current-mode exponential circuit

Cheng

Lin

Chen³

2019

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

A CMOS current-mode exponential circuit is designed by plugging candidate circuits into a Taylor's approximation circuit to make a multiple-segment circuit. The selection of candidate circuits is dependent on a large linearity range in each segment. The proposed range-segmented circuit is different from all segments constructed only by quadratic circuits or only by linear circuits. The proposed circuit was simulated using UMC 0.18 µ m CMOS technology. The output linearity of the circuit is 56.7 dB for gain error less than 0.5 dB, and the-3 dB bandwidth of the circuit is between 69 and 150 MHz for input range from-63 to 198 µ A.

show abstract

A conductance-based neuronal network in VLSI for studying the CPR circuit of the crayfish

Chen

2012

2012 IEEE International Symposium on Circuits and Systems

View full text Add to dashboard Cite

Current-Mode Computation with Noise in a Scalable and Programmable Probabilistic Neural VLSI System

Cited by 6 publications

References 10 publications

A Survey of Neuromorphic Computing and Neural Networks in Hardware

A Survey of Neuromorphic Computing and Neural Networks in Hardware

Design of a range-segmented CMOS current-mode exponential circuit

A conductance-based neuronal network in VLSI for studying the CPR circuit of the crayfish

Contact Info

Product

Resources

About