Building Brain-Inspired Computing Systems: Examining the Role of Nanoscale Devices

Nandakumar, S. R.; Kulkarni, Shruti; Babu, Anakha V; Rajendran, Bipin

doi:10.1109/mnano.2018.2845078

Cited by 36 publications

(19 citation statements)

References 108 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, due to its in-memory computation capability, crossbar arrays are estimated to outperform modern GPUs by four orders of magnitude 31 . This is particularly advantageous for SNNs, as it need continuous time simulation which calls for more analog and inherently parallel architectures 32 . The computational efficiency of the crossbar array could be maintained to a large extent in the ANN training if its weight-update stage could also be performed directly on the array devices, based on the coincidence of stochastic pulses that represent the neuronal activations and back-propagated errors.…”

Section: Discussionmentioning

confidence: 99%

A phase-change memory model for neuromorphic computing

Nandakumar

Gallo

Boybat

et al. 2018

Journal of Applied Physics

Self Cite

122

View full text Add to dashboard Cite

Phase-change memory (PCM) is an emerging non-volatile memory technology that is based on the reversible and rapid phase transition between the amorphous and crystalline phases of certain phase-change materials. The ability to alter the conductance levels in a controllable way makes PCM devices particularly well-suited for synaptic realizations in neuromorphic computing. A key attribute that enables this application is the progressive crystallization of the phase-change material and subsequent increase in device conductance by the successive application of appropriate electrical pulses. There is significant inter and intra-device randomness associated with this cumulative conductance evolution and it is essential to develop a statistical model to capture this. PCM also exhibits a temporal evolution of the conductance values (drift) which could also influence applications in neuromorphic computing. In this paper, we have developed a statistical model that describes both the cumulative conductance evolution and conductance drift. This model is based on extensive characterization work on 10,000 memory devices. Finally, the model is used to simulate supervised training of both spiking and non-spiking artificial neuronal networks.

show abstract

Section: Discussionmentioning

confidence: 99%

A phase-change memory model for neuromorphic computing

Nandakumar

Gallo

Boybat

et al. 2018

Journal of Applied Physics

Self Cite

122

View full text Add to dashboard Cite

show abstract

“…and decompose matrices H = {H i j }, B = {B i j }, i, j = 1, 2, and vector U(t; t 0 ) = {U i (t; t 0 )}, i = 1, 2. Substituting (2)- (5) in (1) we obtain that the SEs of N in the (ϕ, q)-domain can be expressed as [18]…”

Section: A State Equations In the (ϕ Q)-domainmentioning

confidence: 99%

Unfolding Nonlinear Dynamics in Analogue Systems With Mem-Elements

Marco

Forti

Corinto

et al. 2021

IEEE Trans. Circuits Syst. I

View full text Add to dashboard Cite

The paper considers a relevant class of networks containing memristors and (possibly) nonlinear capacitors and inductors. The goal is to unfold the nonlinear dynamics of these networks by highlighting some main features that are potentially useful for real-time signal processing and in-memory computing. In particular, an analytic treatment is provided for dynamic phenomena as the presence of invariant manifolds, the coexistence of different regimes, complex dynamics and attractors and the phenomenon of bifurcations without parameters, i.e., bifurcations due to changing the initial conditions of the state variables for a fixed set of circuit parameters. The paper also addresses the issue of how to design pulse independent voltage or current sources to steer the network dynamics through different manifolds and attractors. Two relevant examples are worked out in details, namely, a variant of Chua's circuit with a memristor and a nonlinear capacitor and a relaxation oscillator with a memristor and a nonlinear inductor. In the latter example, the paper also studies the effect on manifolds and coexisting dynamics when real memristive devices are accounted for using a class of extended memristor models. The analysis is conducted by means of a recently developed technique named flux-charge analysis method (FCAM). Numerical simulations are presented to confirm the theoretic findings.

show abstract

“…An MPNN consumes power only during the short analog transient with potential advantages in terms of power consumption over NNs computing in the voltage-current domain, where voltages, current, and power do not vanish in the steady state. 2) An MPNN works in accordance with the fundamental principle of in-memory computing [10], [13], [14]. Indeed, the role of memristors is two-fold: their nonlinearity is used for analog computation purposes, moreover, memristors are also used to store in a nonvolatile way the result of computation.…”

Section: Introductionmentioning

confidence: 99%

Memristor Neural Networks for Linear and Quadratic Programming Problems

Marco

Forti

Pancioni

et al. 2022

IEEE Trans. Cybern.

View full text Add to dashboard Cite

This article introduces a new class of memristor neural networks (NNs) for solving, in real-time, quadratic programming (QP) and linear programming (LP) problems. The networks, which are called memristor programming NNs (MPNNs), use a set of filamentary-type memristors with sharp memristance transitions for constraint satisfaction and an additional set of memristors with smooth memristance transitions for memorizing the result of a computation. The nonlinear dynamics and global optimization capabilities of MPNNs for QP and LP problems are thoroughly investigated via a recently introduced technique called the flux-charge analysis method. One main feature of MPNNs is that the processing is performed in the fluxcharge domain rather than in the conventional voltage-current domain. This enables exploiting the unconventional features of memristors to obtain advantages over the traditional NNs for QP and LP problems operating in the voltage-current domain. One advantage is that operating in the flux-charge domain allows for reduced power consumption, since in an MPNN, voltages, currents, and, hence, power vanish when the quick analog transient is over. Moreover, an MPNN works in accordance with the fundamental principle of in-memory computing, that is, the nonlinearity of the memristor is used in the dynamic computation, but the same memristor is also used to memorize in a nonvolatile way the result of a computation.

show abstract

Building Brain-Inspired Computing Systems: Examining the Role of Nanoscale Devices

Cited by 36 publications

References 108 publications

A phase-change memory model for neuromorphic computing

A phase-change memory model for neuromorphic computing

Unfolding Nonlinear Dynamics in Analogue Systems With Mem-Elements

Memristor Neural Networks for Linear and Quadratic Programming Problems

Contact Info

Product

Resources

About