Modeling and Experimental Demonstration of a Hopfield Network Analog-to-Digital Converter with Hybrid CMOS/Memristor Circuits

Guo, Xin; Merrikh-Bayat, Farshad; Gao, Ligang; Hoskins, Brian D.; Alibart, Fabien; Linares-Barranco, B.; Theogarajan, Luke; Teuscher, Christof; Strukov, Dmitri B.

doi:10.3389/fnins.2015.00488

Cited by 59 publications

(65 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, in [26] the hybrid CMOS-memristor Hopfield network-based associative memory is demonstrated. While in the work conducted by Guo et al [27], the CMOS-memristor hybrid architecture is applied in the design of 4-bit Hopfield neural ADC. Figure 10 reflects the schematic of the system proposed in [27].…”

Section: Cmos/memristor Hybrid Network-based Adcmentioning

confidence: 99%

“…While in the work conducted by Guo et al [27], the CMOS-memristor hybrid architecture is applied in the design of 4-bit Hopfield neural ADC. Figure 10 reflects the schematic of the system proposed in [27].…”

Section: Cmos/memristor Hybrid Network-based Adcmentioning

confidence: 99%

“…The CMOS-memristor hybrid Hopfield ADC [27] consists of memristor-based weight matrix and sigmoidal CMOS neurons. The advantage of implementing constant synapses (in Hopfield NN for ADC design synaptic weights a preset and kept unchanged [11]) with memristors is that being a nanoscale device, memristors consume much less power [27].…”

Section: Cmos/memristor Hybrid Network-based Adcmentioning

confidence: 99%

“…The advantage of implementing constant synapses (in Hopfield NN for ADC design synaptic weights a preset and kept unchanged [11]) with memristors is that being a nanoscale device, memristors consume much less power [27]. Moreover, they significantly reduce the on-chip area compared to CMOS-based synaptic weights [27].…”

Section: Cmos/memristor Hybrid Network-based Adcmentioning

confidence: 99%

See 3 more Smart Citations

Neural Network-Based Analog-to-Digital Converters

Tankimanova¹,

James²

2018

Memristor and Memristive Neural Networks

View full text Add to dashboard Cite

In this chapter, we present an overview of the recent advances in analog-to-digital converter (ADC) neural networks. Biological neural networks consist of natural binarization reflected by the neurosynaptic processes. This natural analog-to-binary conversion ability of neurons can be modeled to emulate analog-to-digital conversion using a set of nonlinear circuit elements and existing artificial neural network models. Since one neuron during processing consumes on average only about half nanowatts of power, neurons can perform highly energy-efficient operations, including pattern recognition. Analog-to-digital conversion itself is an example of simple pattern recognition where input analog signal can be presented in one of the 2 N different patterns for N bits. The classical configuration of neural network-based ADC is Hopfield neural network ADC. Improved designs, such as modified Hopfield network ADC, T-model neural ADC, and multilevel neurons-based neural ADC, will be discussed. In addition, the latest architecture designs of neural ADC such as hybrid complementary metal-oxide semiconductor (CMOS)-memristor Hopfield ADC are covered at the end of this chapter.

show abstract

Section: Cmos/memristor Hybrid Network-based Adcmentioning

confidence: 99%

Section: Cmos/memristor Hybrid Network-based Adcmentioning

confidence: 99%

Section: Cmos/memristor Hybrid Network-based Adcmentioning

confidence: 99%

Section: Cmos/memristor Hybrid Network-based Adcmentioning

confidence: 99%

See 2 more Smart Citations

Neural Network-Based Analog-to-Digital Converters

Tankimanova¹,

James²

2018

Memristor and Memristive Neural Networks

View full text Add to dashboard Cite

show abstract

“…[15][16][17][18][19][20][21][22] However, it is important to stress that the machines we propose need feedback to operate as we desire. 5 Therefore, memelements alone are not enough.…”

mentioning

confidence: 99%

Perspective: Memcomputing: Leveraging memory and physics to compute efficiently

Ventra

Traversa

2018

Journal of Applied Physics

View full text Add to dashboard Cite

It is well known that physical phenomena may be of great help in computing some difficult problems efficiently. A typical example is prime factorization that may be solved in polynomial time by exploiting quantum entanglement on a quantum computer. There are, however, other types of (non-quantum) physical properties that one may leverage to compute efficiently a wide range of hard problems. In this perspective we discuss how to employ one such property, memory (time non-locality), in a novel physics-based approach to computation: Memcomputing. In particular, we focus on digital memcomputing machines (DMMs) that are scalable. DMMs can be realized with non-linear dynamical systems with memory. The latter property allows the realization of a new type of Boolean logic, one that is self-organizing. Self-organizing logic gates are "terminal-agnostic", namely they do not distinguish between input and output terminals. When appropriately assembled to represent a given combinatorial/optimization problem, the corresponding self-organizing circuit converges to the equilibrium points that express the solutions of the problem at hand. In doing so, DMMs take advantage of the long-range order that develops during the transient dynamics. This collective dynamical behavior, reminiscent of a phase transition, or even the "edge of chaos", is mediated by families of classical trajectories (instantons) that connect critical points of increasing stability in the system's phase space. The topological character of the solution search renders DMMs robust against noise and structural disorder. Since DMMs are non-quantum systems described by ordinary differential equations, not only can they be built in hardware with available technology, they can also be simulated efficiently on modern classical computers. As an example, we will show the polynomial-time solution of the subset-sum problem for the worst cases, and point to other types of hard problems where simulations of DMMs' equations of motion on classical computers have already demonstrated substantial advantages over traditional approaches. We conclude this article by outlining further directions of study.

show abstract

Modeling the Metal–Insulator Phase Transition in Li_xCoO₂ for Energy and Information Storage

Nadkarni

Zhou

Fraggedakis

et al. 2019

Adv Funct Materials

View full text Add to dashboard Cite

An electro-chemomechanical phase-field model is developed to capture the metal-insulator phase transformation along with the structural and chemical changes that occur in Li x CoO 2 in the regular operating range of 0.5 < x < 1. Under equilibrium, in the regime of phase coexistence, it is found that transport limitations lead to kinetically arrested states that are not determined by strain-energy minimization. Further, lithiation profiles are obtained for different discharging rates and the experimentally observed voltage plateau is observed. Finally, a simple model is developed to account for the conductivity changes for a polycrystalline Li x CoO 2 thin film as it transforms from the metallic phase to the insulating phase and a strategy is outlined for memristor design. The theory can therefore be used for modeling Li x CoO 2 -electrode batteries as well as low voltage nonvolatile redox transistors for neuromorphic computing architectures.The ORCID identification number(s) for the author(s) of this article can be found under https://doi.org/10.1002/adfm.201902821. the lithiation process, the crystal structure of LCO remains unchanged with the host lattice contracting along the c-axis. [8,12,13] Another important characteristic of LCO is the metal-insulator transition, in which the material transitions from a good (x < 0.75) to a poor (x > 0.94) electron conductor. [8,21,25] The metal-insulator phase coexistence, during the transition, is observed macroscopically through a voltage plateau in the voltage versus state of charge diagram, occurring over the entire range of 0.75 < x < 0.94. [13,21,25] The layered structure of LCO allows for Li to diffuse only in the plane perpendicular to the [0001] direction, leading to effectively 2D transport in the crystal. [11,26] LCO is therefore a widely studied material and has been in commercial use in battery technology for over three decades. [1,2] Thus, developing a predictive mesoscopic model is paramount in studying the nonequilibrium charging/discharging as well as phase-separating behavior for this material.Recently, there has been renewed interest in LCO because of its metal-insulator transition behavior for the development of nonvolatile redox memristors to be used in neuromorphic computing technology. [27] In order to mimic the efficiency of the human brain, neuromorphic computing architecture is becoming an exciting avenue toward development of hardware specialized for machine learning and pattern recognition algorithms. [28][29][30] Current CMOS technologies consume high energy due to the movement of data between the processor, and static and dynamic random access memory. [27,31] In contrast, resistive memory crossbars, in which processing and memory storage occurs simultaneously, have been predicted to lower this energy requirement by six orders of magnitude. [32,33] The memristor, first proposed by Leon Chua, is the unit circuit element that forms the basis of this architecture. [34] The current state-of-the-art memristors, e.g., phase-change memories (PCM) [35...

show abstract

Modeling and Experimental Demonstration of a Hopfield Network Analog-to-Digital Converter with Hybrid CMOS/Memristor Circuits

Cited by 59 publications

References 27 publications

Neural Network-Based Analog-to-Digital Converters

Neural Network-Based Analog-to-Digital Converters

Perspective: Memcomputing: Leveraging memory and physics to compute efficiently

Modeling the Metal–Insulator Phase Transition in Li_xCoO₂ for Energy and Information Storage

Contact Info

Product

Resources

About

Modeling and Experimental Demonstration of a Hopfield Network Analog-to-Digital Converter with Hybrid CMOS/Memristor Circuits

Cited by 59 publications

References 27 publications

Neural Network-Based Analog-to-Digital Converters

Neural Network-Based Analog-to-Digital Converters

Perspective: Memcomputing: Leveraging memory and physics to compute efficiently

Modeling the Metal–Insulator Phase Transition in LixCoO2 for Energy and Information Storage

Contact Info

Product

Resources

About

Modeling the Metal–Insulator Phase Transition in Li_xCoO₂ for Energy and Information Storage