Emulating short-term synaptic dynamics with memristive devices

Berdan, Radu; Vasilaki, Eleni; Khiat, Ali; Indiveri, Giacomo; Serb, Alexantrou; Prodromakis, Themis

doi:10.1038/srep18639

Cited by 116 publications

(88 citation statements)

References 77 publications

(92 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, a drastic research paradigm shift toward memristive devices may enable a new approach of full memristive neural networks (FMNN) for achieving bioplausible neural networks with great scaling potential . Significant progress has been made on memristive synapses, which can simulate rich synaptic functionalities on a single nanodevice . Especially, by utilizing the dynamic memory switching effect, memristors has been proposed to simulate the synaptic learning rules, leading to a more biological artificial synapse.…”

Section: Introductionmentioning

confidence: 99%

“…[7][8][9] Significant progress has been made on memristive synapses, which can simulate rich synaptic functionalities on a single nanodevice. [10][11][12][13][14][15][16][17] Especially, by utilizing the dynamic memory switching effect, memristors has been proposed to simulate the synaptic learning rules, [14][15][16][17] leading to a more biological artificial synapse. In contrast, artificial memristive neurons are rarely reported despite of its equal importance.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Highly Compact Artificial Memristive Neuron with Low Energy Consumption

Zhang

et al. 2018

Small

View full text Add to dashboard Cite

Neuromorphic systems aim to implement large‐scale artificial neural network on hardware to ultimately realize human‐level intelligence. The recent development of nonsilicon nanodevices has opened the huge potential of full memristive neural networks (FMNN), consisting of memristive neurons and synapses, for neuromorphic applications. Unlike the widely reported memristive synapses, the development of artificial neurons on memristive devices has less progress. Sophisticated neural dynamics is the major obstacle behind the lagging. Here a rich dynamics‐driven artificial neuron is demonstrated, which successfully emulates partial essential neural features of neural processing, including leaky integration, automatic threshold‐driven fire, and self‐recovery, in a unified manner. The realization of bioplausible artificial neurons on a single device with ultralow power consumption paves the way for constructing energy‐efficient large‐scale FMNN and may boost the development of neuromorphic systems with high density, low power, and fast speed.

show abstract

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

Highly Compact Artificial Memristive Neuron with Low Energy Consumption

Zhang

et al. 2018

Small

View full text Add to dashboard Cite

show abstract

“…While there are examples of hybrid memristive-CMOS hardware architectures being developed to provide support for AI deep network accelerators 5,11,14,15 , it is important to clarify that many of the hybrid memristive-CMOS neuromorphic arXiv:1912.05637v1 [cs.ET] 11 Dec 2019 circuits proposed in the literature [16][17][18][19][20] as well as the original neuromorphic approach of emulating biological neural systems proposed by Mead, are distinct and complementary to the machine learning one. While the machine learning approach is based on software algorithms developed to minimize the recognition error in very specific pattern recognition tasks, the original neuromorphic approach is based on brain-inspired electronic circuits and hardware architectures designed for reproducing the function of cortical and biological neural circuits 21 .…”

mentioning

confidence: 99%

A recipe for creating ideal hybrid memristive-CMOS neuromorphic processing systems

Chicca

Indiveri

2020

Applied Physics Letters

View full text Add to dashboard Cite

The development of memristive device technologies has reached a level of maturity to enable the design of complex and large-scale hybrid memristive-CMOS neural processing systems. These systems offer promising solutions for implementing novel in-memory computing architectures for machine learning and data analysis problems. We argue that they are also ideal building blocks for the integration in neuromorphic electronic circuits suitable for ultra-low power brain-inspired sensory processing systems, therefore leading to the innovative solutions for always-on edge-computing and Internet-of-Things (IoT) applications. Here we present a recipe for creating such systems based on design strategies and computing principles inspired by those used in mammalian brains. We enumerate the specifications and properties of memristive devices required to support always-on learning in neuromorphic computing system and to minimize their power consumption. Finally, we discuss in what cases such neuromorphic systems can complement conventional processing ones and highlight the importance of exploiting the physics of both the memristive devices and of the CMOS circuits interfaced to them.Neuromorphic computing has recently received considerable attention as a discipline that can offer promising technological solutions for implementing power-and size-efficient sensory-processing, learning, and Artificial Intelligence (AI) applications 1-5 , especially in cases in which the computing system has to operate autonomously "at the edge", i.e., without having to connect to powerful (but power hungry) server farms in the "cloud". The term "neuromorphic" was originally coined in the early 90's by Carver Mead to refer to mixed signal analog/digital Very Large Scale Integration (VLSI) computing systems based on the organizing principles used by the biological nervous systems 6 . In that context, "neuromorphic engineering" emerged as an interdisciplinary research field deeply rooted in biology that focused on building electronic neural processing systems by exploiting the physics of silicon to directly "emulate" the bio-physics of real neurons and synapses. More recently the definition of the term "neuromorphic" has been extended in two additional directions: on one hand to describe more generic spike-based processing systems engineered to "simulate" spiking neural networks for the exploration of large-scale computational neuroscience models 7-9 ; and on the other hand to describe dedicated electronic neural architectures that make use of both electronic Complementary Metal-Oxide Semiconductor (CMOS) circuits and memristive devices to implement neuron and synapse circuits 10,11 .Another recent and very promising trend in developing dedicated hardware architectures for building accelerated simulators of artificial neural networks is related to the field of machine learning and AI 12,13 . The types of neural networks being proposed within this context are only loosely inspired by biology, are aimed at high accuracy pattern recognition based on large...

show abstract

“…The devices present excellent retention characteristics with minimal state deviations even after long cycles of operation. Additionally to increased memory density, the multi-bit capabilities of the memristors can be used towards logic scaling 10,33 through the replacement of large MOS-based circuits with few nanoscale memristive devices, in technologies such as TLGs [34][35][36][37] . Furthermore, the use of memristors as continuously tuneable resistive devices is enabling the scaling in area and power of the TLGs, previously impracticable in VLSI technology due to limitation of the MOSFET devices.…”

Section: Fundamental Components: Tlg Theory and Memristor Technologymentioning

confidence: 99%

Practical Implementation of Memristor-Based Threshold Logic Gates

Papandroulidakis

Serb

Khiat

et al. 2019

IEEE Trans. Circuits Syst. I

Self Cite

View full text Add to dashboard Cite

Current advances in emerging memory technologies enable novel and unconventional computing architectures for high-performance and low-power electronic systems, capable of carrying out massively parallel operations at the edge. One emerging technology, ReRAM, also known to belong in the family of memristors (memory resistors), is gathering attention due to its attractive features for logic and in-memory computing; benefits which follow from its technological attributes, such as nanoscale dimensions, low power operation and multi-state programming. At the same time, design with CMOS is quickly reaching its physical and functional limitations, and further research towards novel logic families, such as Threshold Logic Gates (TLGs) is scoped. TLGs constitute a logic family known for its high-speed and low power consumption, yet rely on conventional transistor technology. Introducing memristors enables a more affordable reconfiguration capability of TLGs. Through this work, we are introducing a physical implementation of a memristor-based currentmode TLG (MCMTLG) circuit and validate its design and operation through multiple experimental setups. We demonstrate 2-input and 3-input MCMTLG configurations and showcase their reconfiguration capability. This is achieved by varying memristive weights arbitrarily for shaping the classification decision boundary, thus showing promise as an alternative hardware-friendly implementation of Artificial Neural Networks (ANNs). Through the employment of real memristor devices as the equivalent of synaptic weights in TLGs, we are realizing components that can be used towards an in-silico classifier.Today's conventional computing paradigm is based on the MOSFET transistor and CMOS technology; two cornerstones which have underpinned the development of digital electronics over the last 5 decades. Although there is still optimism for future improvement of CMOS, accumulating scientific evidence indicates the need for advances in both new emerging technologies to replace MOSFETs and in new computer circuits and architectures 1,2 . The former addresses the increasing difficulty of pursuing further downscaling (with its associated drop in reliability 2 ) whilst the latter seeks to address the Von Neumann bottleneck, where increasingly big memories and powerful processors struggle to communicate over a limited interlink whose data transfer capacity doesn't scale fast enough 2-4 .On the computation/architecture front, there has been a sustained effort to develop bio-inspired computation concepts, mostly in the guise of artificial neural network-enabled (ANN) systems. Research on artificial neural networks has thus far spanned the entire interval between the first simplified models of all-or-none hardware neurons 5 and the current state-of-the-art GPU-based ANNs 6-8 . However, one often overlooked example of ANN-like computation can be found in the form of its quantized, digital counterpart, the so-called threshold logic (TL). TL is a model for performing a

show abstract

Emulating short-term synaptic dynamics with memristive devices

Cited by 116 publications

References 77 publications

Highly Compact Artificial Memristive Neuron with Low Energy Consumption

Highly Compact Artificial Memristive Neuron with Low Energy Consumption

A recipe for creating ideal hybrid memristive-CMOS neuromorphic processing systems

Practical Implementation of Memristor-Based Threshold Logic Gates

Contact Info

Product

Resources

About