arXiv subjects

Damien Querlioz

Publications and source records attributed to Damien Querlioz.

67 records · Page 4Linked to original sources

arXiv2018

Overcoming device unreliability with continuous learning in a population coding based computing system

The brain, which uses redundancy and continuous learning to overcome the unreliability of its components, provides a promising path to building computing systems that are robust to the unreliability of their constituent nanodevices. In this work, we illustrate this path by a computing system based on population coding with magnetic tunnel junctions that implement both neurons and synaptic weights. We show that equipping such a system with continuous learning enables it to recover from the loss of neurons and makes it possible to use unreliable synaptic weights (i.e. low energy barrier magnetic memories). There is a tradeoff between power consumption and precision because low energy barrier memories consume less energy than high barrier ones. For a given precision, there is an optimal number of neurons and an optimal energy barrier for the weights that leads to minimum power consumption.

cs.ET↗

arXiv2018

Resonate and Fire Neuron with Fixed Magnetic Skyrmions

In the brain, the membrane potential of many neurons oscillates in a subthreshold damped fashion and fire when excited by an input frequency that nearly equals their eigen frequency. In this work, we investigate theoretically the artificial implementation of such "resonate-and-fire" neurons by utilizing the magnetization dynamics of a fixed magnetic skyrmion in the free layer of a magnetic tunnel junction (MTJ). To realize firing of this nanomagnetic implementation of an artificial neuron, we propose to employ voltage control of magnetic anisotropy or voltage generated strain as an input (spike or sinusoidal) signal, which modulates the perpendicular magnetic anisotropy (PMA). This results in continual expansion and shrinking (i.e. breathing) of a skyrmion core that mimics the subthreshold oscillation. Any subsequent input pulse having an interval close to the breathing period or a sinusoidal input close to the eigen frequency drives the magnetization dynamics of the fixed skyrmion in a resonant manner. The time varying electrical resistance of the MTJ layer due to this resonant oscillation of the skyrmion core is used to drive a Complementary Metal Oxide Semiconductor (CMOS) buffer circuit, which produces spike outputs. By rigorous micromagnetic simulation, we investigate the interspike timing dependence and response to different excitatory and inhibitory incoming input pulses. Finally, we show that such resonate and fire neurons have potential application in coupled nanomagnetic oscillator based associative memory arrays.

physics.app-ph↗

arXiv2018

Neural-like computing with populations of superparamagnetic basis functions

In neuroscience, population coding theory demonstrates that neural assemblies can achieve fault-tolerant information processing. Mapped to nanoelectronics, this strategy could allow for reliable computing with scaled-down, noisy, imperfect devices. Doing so requires that the population components form a set of basis functions in terms of their response functions to inputs, offering a physical substrate for calculating. For this purpose, the responses of the nanodevices should be non-linear, and each tuned to different values of the input. These strong requirements have prevented a demonstration of population coding with nanodevices. Here, we show that nanoscale magnetic tunnel junctions can be assembled to meet these requirements. We demonstrate experimentally that a population of nine junctions can implement a basis set of functions, providing the data to achieve, for example, the generation of cursive letters. We design hybrid magnetic-CMOS systems based on interlinked populations of junctions and show that they can learn to realize non-linear variability-resilient transformations with a low imprint area and low power.

cs.ET↗

arXiv2017

Low-Energy Truly Random Number Generation with Superparamagnetic Tunnel Junctions for Unconventional Computing

Low-energy random number generation is critical for many emerging computing schemes proposed to complement or replace von Neumann architectures. However, current random number generators are always associated with an energy cost that is prohibitive for these computing schemes. In this paper, we introduce random number bit generation based on specific nanodevices: superparamagnetic tunnel junctions. We experimentally demonstrate high quality random bit generation that represents orders-of-magnitude improvements in energy efficiency compared to current solutions. We show that the random generation speed improves with nanodevice scaling, and investigate the impact of temperature, magnetic field and crosstalk. Finally, we show how alternative computing schemes can be implemented using superparamagentic tunnel junctions as random number generators. These results open the way for fabricating efficient hardware computing devices leveraging stochasticity, and highlight a novel use for emerging nanodevices.

physics.app-ph↗

arXiv2017

Skyrmion Gas Manipulation for Probabilistic Computing

The topologically protected magnetic spin configurations known as skyrmions offer promising applications due to their stability, mobility and localization. In this work, we emphasize how to leverage the thermally driven dynamics of an ensemble of such particles to perform computing tasks. We propose a device employing a skyrmion gas to reshuffle a random signal into an uncorrelated copy of itself. This is demonstrated by modelling the ensemble dynamics in a collective coordinate approach where skyrmion-skyrmion and skyrmion-boundary interactions are accounted for phenomenologically. Our numerical results are used to develop a proof-of-concept for an energy efficient ($\simμ\mathrm{W}$) device with a low area imprint ($\simμ\mathrm{m}^2$). Whereas its immediate application to stochastic computing circuit designs will be made apparent, we argue that its basic functionality, reminiscent of an integrate-and-fire neuron, qualifies it as a novel bio-inspired building block.

cond-mat.mes-hall↗

arXiv2017

Spatio-temporal Learning with Arrays of Analog Nanosynapses

Emerging nanodevices such as resistive memories are being considered for hardware realizations of a variety of artificial neural networks (ANNs), including highly promising online variants of the learning approaches known as reservoir computing (RC) and the extreme learning machine (ELM). We propose an RC/ELM inspired learning system built with nanosynapses that performs both on-chip projection and regression operations. To address time-dynamic tasks, the hidden neurons of our system perform spatio-temporal integration and can be further enhanced with variable sampling or multiple activation windows. We detail the system and show its use in conjunction with a highly analog nanosynapse device on a standard task with intrinsic timing dynamics- the TI-46 battery of spoken digits. The system achieves nearly perfect (99%) accuracy at sufficient hidden layer size, which compares favorably with software results. In addition, the model is extended to a larger dataset, the MNIST database of handwritten digits. By translating the database into the time domain and using variable integration windows, up to 95% classification accuracy is achieved. In addition to an intrinsically low-power programming style, the proposed architecture learns very quickly and can easily be converted into a spiking system with negligible loss in performance- all features that confer significant energy efficiency.

cs.NE↗

arXiv2017

A Neural Network Based on Synchronized Pairs of Nano-Oscillators

Artificial neural networks are intensively used to perform cognitive tasks such as image classification on traditional computers. With the end of CMOS scaling and increasing demand for efficient neural networks, alternative architectures implementing neural functions efficiently are being studied. This study leverages the demonstrated frequency tuning capabilities of compact nano-oscillators and their synchronization dynamics to implement a neuron using a pair of synchronized oscillators, and which features an unconventional response curve. We show that this compact neuron can naturally implement generic logic gates, including XOR. A simulated oscillator-based neural network is then shown to achieve results equivalent to standard approaches on two reference classification tasks. Finally, the performance of the system is evaluated in the presence of oscillator phase noise, an important issue of oscillating nanodevices. These results open the way for the design of alternative architectures adapted to efficient neural network execution.

cs.ET↗

arXiv2017

Neuromorphic computing with nanoscale spintronic oscillators

Neurons in the brain behave as non-linear oscillators, which develop rhythmic activity and interact to process information. Taking inspiration from this behavior to realize high density, low power neuromorphic computing will require huge numbers of nanoscale non-linear oscillators. Indeed, a simple estimation indicates that, in order to fit a hundred million oscillators organized in a two-dimensional array inside a chip the size of a thumb, their lateral dimensions must be smaller than one micrometer. However, despite multiple theoretical proposals, there is no proof of concept today of neuromorphic computing with nano-oscillators. Indeed, nanoscale devices tend to be noisy and to lack the stability required to process data in a reliable way. Here, we show experimentally that a nanoscale spintronic oscillator can achieve spoken digit recognition with accuracies similar to state of the art neural networks. We pinpoint the regime of magnetization dynamics leading to highest performance. These results, combined with the exceptional ability of these spintronic oscillators to interact together, their long lifetime, and low energy consumption, open the path to fast, parallel, on-chip computation based on networks of oscillators.

cs.ET↗

arXiv2016

Role of spin-transfer torques on synchronization and resonance phenomena in stochastic magnetic oscillators

A theoretical study on how synchronization and resonance-like phenomena in superparamagnetic tunnel junctions can be driven by spin-transfer torques is presented. We examine the magnetization of a superparamagnetic free layer that reverses randomly between two well-defined orientations due to thermal fluctuations, acting as a stochastic oscillator. When subject to an external ac forcing this system can present stochastic resonance and noise-enhanced synchronization. We focus on the roles of the mutually perpendicular damping-like and field-like torques, showing that the response of the system is very different at low and high-frequencies. We also demonstrate that the field-like torque can increase the efficiency of the current-driven forcing, specially at sub-threshold electric currents. These results can be useful for possible low-power, more energy efficient, applications.

cond-mat.mes-hall↗

arXiv2016

Spintronic nano-devices for bio-inspired computing

Bio-inspired hardware holds the promise of low-energy, intelligent and highly adaptable computing systems. Applications span from automatic classification for big data management, through unmanned vehicle control, to control for bio-medical prosthesis. However, one of the major challenges of fabricating bio-inspired hardware is building ultra-high density networks out of complex processing units interlinked by tunable connections. Nanometer-scale devices exploiting spin electronics (or spintronics) can be a key technology in this context. In particular, magnetic tunnel junctions are well suited for this purpose because of their multiple tunable functionalities. One such functionality, non-volatile memory, can provide massive embedded memory in unconventional circuits, thus escaping the von-Neumann bottleneck arising when memory and processors are located separately. Other features of spintronic devices that could be beneficial for bio-inspired computing include tunable fast non-linear dynamics, controlled stochasticity, and the ability of single devices to change functions in different operating conditions. Large networks of interacting spintronic nano-devices can have their interactions tuned to induce complex dynamics such as synchronization, chaos, soliton diffusion, phase transitions, criticality, and convergence to multiple metastable states. A number of groups have recently proposed bio-inspired architectures that include one or several types of spintronic nanodevices. In this article we show how spintronics can be used for bio-inspired computing. We review the different approaches that have been proposed, the recent advances in this direction, and the challenges towards fully integrated spintronics-CMOS (Complementary metal - oxide - semiconductor) bio-inspired hardware.

cs.ET↗

arXiv2016

Synchronization Detection in Networks of Coupled Oscillators for Pattern Recognition

Coupled oscillator-based networks are an attractive approach for implementing hardware neural networks based on emerging nanotechnologies. However, the readout of the state of a coupled oscillator network is a difficult challenge in hardware implementations, as it necessitates complex signal processing to evaluate the degree of synchronization between oscillators, possibly more complicated than the coupled oscillator network itself. In this work, we focus on a coupled oscillator network particularly adapted to emerging technologies, and evaluate two schemes for reading synchronization patterns that can be readily implemented with basic CMOS circuits. Through simulation of a simple generic coupled oscillator network, we compare the operation of these readout techniques with a previously proposed full statistics evaluation scheme. Our approaches provide results nearly identical to the mathematical method, but also show better resilience to moderate noise, which is a major concern for hardware implementations. These results open the door to widespread realization of hardware coupled oscillator-based neural systems.

cs.ET↗

arXiv2016

Exploiting the Short-term to Long-term Plasticity Transition in Memristive Nanodevice Learning Architectures

Memristive nanodevices offer new frontiers for computing systems that unite arithmetic and memory operations on-chip. Here, we explore the integration of electrochemical metallization cell (ECM) nanodevices with tunable filamentary switching in nanoscale learning systems. Such devices offer a natural transition between short-term plasticity (STP) and long-term plasticity (LTP). In this work, we show that this property can be exploited to efficiently solve noisy classification tasks. A single crossbar learning scheme is first introduced and evaluated. Perfect classification is possible only for simple input patterns, within critical timing parameters, and when device variability is weak. To overcome these limitations, a dual-crossbar learning system partly inspired by the extreme learning machine (ELM) approach is then introduced. This approach outperforms a conventional ELM-inspired system when the first layer is imprinted before training and testing, and especially so when variability in device timing evolution is considered: variability is therefore transformed from an issue to a feature. In attempting to classify the MNIST database under the same conditions, conventional ELM obtains 84% classification, the imprinted, uniform device system obtains 88% classification, and the imprinted, variable device system reaches 92% classification. We discuss benefits and drawbacks of both systems in terms of energy, complexity, area imprint, and speed. All these results highlight that tuning and exploiting intrinsic device timing parameters may be of central interest to future bio-inspired approximate computing systems.

cs.NE↗

arXiv2014

Noise-enhanced synchronization of stochastic magnetic oscillators

We present an experimental study of phase-locking in a stochastic magnetic oscillator. The system comprises a magnetic tunnel junction with a superparamagnetic free layer, whose magnetization dynamics is driven with spin torques through an external periodic driving current. We show that synchronization of this stochastic oscillator to the input current is possible for current densities below $3 \times 10^6$ A/cm$^2$, and occurs for input frequencies lower than the natural mean frequency of the stochastic oscillator. We show that such injection-locking is robust and leads to a drastic reduction in the phase diffusion of the stochastic oscillator, despite the presence of a frequency mismatch between the oscillator and the excitation.

cond-mat.mtrl-sci↗