Stochastic neuron design using conductive bridge RAM

Palma, Giorgio; Suri, Manan; Querlioz, Damien; Vianello, E.; Salvo, B. De

doi:10.1109/nanoarch.2013.6623051

Cited by 25 publications

(16 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our proposed architecture works for stochastic computing as well, however, a stochastic firing mechanism is needed for the silicon neuron implementation instead of deterministic firing. Leveraging the stochastic behavior of nano-devices, a solution was proposed in [77] but its hardware realization feasibility still needs evaluation. Finally, it should be noted that the circuit-level simulations with faithful modeling of electrical behavior consumes significant amount of time as well as computing resources.…”

Section: Discussionmentioning

confidence: 99%

Homogeneous Spiking Neuromorphic System for Real-World Pattern Recognition

Saxena

Zhu

2015

IEEE J. Emerg. Sel. Topics Circuits Syst.

View full text Add to dashboard Cite

Abstract-A neuromorphic chip that combines CMOS analog spiking neurons and memristive synapses offers a promising solution to brain-inspired computing, as it can provide massive neural network parallelism and density. Previous hybrid analog CMOS-memristor approaches required extensive CMOS circuitry for training, and thus eliminated most of the density advantages gained by the adoption of memristor synapses. Further, they used different waveforms for pre and post-synaptic spikes that added undesirable circuit overhead. Here we describe a hardware architecture that can feature a large number of memristor synapses to learn real-world patterns. We present a versatile CMOS neuron that combines integrate-and-fire behavior, drives passive memristors and implements competitive learning in a compact circuit module, and enables in-situ plasticity in the memristor synapses. We demonstrate handwritten-digits recognition using the proposed architecture using transistor-level circuit simulations. As the described neuromorphic architecture is homogeneous, it realizes a fundamental building block for large-scale energy-efficient brain-inspired silicon chips that could lead to next-generation cognitive computing.

show abstract

Section: Discussionmentioning

confidence: 99%

Homogeneous Spiking Neuromorphic System for Real-World Pattern Recognition

Saxena

Zhu

2015

IEEE J. Emerg. Sel. Topics Circuits Syst.

View full text Add to dashboard Cite

show abstract

“…Hence, there is no need to dissipate additional power on flushing the membrane capacitance, . Interestingly, memristive stochasticity has already been proposed to introduce variability in the spike trains generated by I&F neurons through random changes of the membrane time constant [39]. Even though this approach begins with a similar motivation, it leads to a different neuron model, namely, leaky I&F model with a time-dependent time constant [64], and hence is different from our proposal.…”

Section: Comparison To the Alternative Proposalsmentioning

confidence: 89%

“…Previously, deterministic memristor models were used to build action potential formation mechanisms similar to Hodgkin-Huxley model [36], [37]. It was also proposed that memristive stochasticity could be used to build binary and continuous-value nonspiking artificial neurons [38] and for adding variability to spike trains generated by leaky I&F neurons [39]. Among other contributions and in contrast to the previous proposals, our design utilizes abrupt memristive switching directly for generating spontaneous events that can be further shaped into spikes.…”

Section: Introductionmentioning

confidence: 99%

Memristors Empower Spiking Neurons With Stochasticity

Al-Shedivat

Naous

Cauwenberghs

et al. 2015

IEEE J. Emerg. Sel. Topics Circuits Syst.

120

View full text Add to dashboard Cite

Recent theoretical studies have shown that probabilistic spiking can be interpreted as learning and inference in cortical microcircuits. This interpretation creates new opportunities for building neuromorphic systems driven by probabilistic learning algorithms. However, such systems must have two crucial features: 1) the neurons should follow a specific behavioral model, and 2) stochastic spiking should be implemented efficiently for it to be scalable. This paper proposes a memristor-based stochastically spiking neuron that fulfills these requirements. First, the analytical model of the memristor is enhanced so it can capture the behavioral stochasticity consistent with experimentally observed phenomena. The switching behavior of the memristor model is demonstrated to be akin to the firing of the stochastic spike response neuron model, the primary building block for probabilistic algorithms in spiking neural networks. Furthermore, the paper proposes a neural soma circuit that utilizes the intrinsic nondeterminism of memristive switching for efficient spike generation. The simulations and analysis of the behavior of a single stochastic neuron and a winner-take-all network built of such neurons and trained on handwritten digits confirm that the circuit can be used for building probabilistic sampling and pattern adaptation machinery in spiking networks. The findings constitute an important step towards scalable and efficient probabilistic neuromorphic platforms.

show abstract

“…Zhang et al [96] present an approach for energy-efficient neuromorphic computing for stochastic learning using multiple perpendicular in-plane magnetic tunnel junctions. Binary Conductive-Bridge RAM (CBRAM) synapses for bio-inspired computing has been presented by Suri et al [97,98], while Querlioz et al [99] discuss stochastic resonance in an analog current-mode circuit.…”

Section: Analog Implementationsmentioning

confidence: 99%

Recent trends in neuromorphic engineering

Soman

Jayadeva

2016

Big Data Anal

Self Cite

View full text Add to dashboard Cite

Neuromorphic Engineering has emerged as an exciting research area, primarily owing to the paradigm shift from conventional computing architectures to data-driven, cognitive computing. There is a diversity of work in the literature pertaining to neuromorphic systems, devices and circuits. This review looks at recent trends in neuromorphic engineering and its sub-domains, with an attempt to identify key research directions that would assume significance in the future. We hope that this review would serve as a handy reference to both beginners and experts, and provide a glimpse into the broad spectrum of applications of neuromorphic hardware and algorithms. Our survey indicates that neuromorphic engineering holds a promising future, particularly with growing data volumes, and the imminent need for intelligent, versatile computing.

show abstract

Stochastic neuron design using conductive bridge RAM

Cited by 25 publications

References 29 publications

Homogeneous Spiking Neuromorphic System for Real-World Pattern Recognition

Homogeneous Spiking Neuromorphic System for Real-World Pattern Recognition

Memristors Empower Spiking Neurons With Stochasticity

Recent trends in neuromorphic engineering

Contact Info

Product

Resources

About