Nanoscale neural network using non-linear spin-wave interference

Papp, Adam; Porod, Wolfgang; Csaba, Gyorgy

doi:10.48550/arxiv.2012.04594

Cited by 8 publications

(15 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the multifunctionality of spintronics also makes it possible to train complex physical systems that do not exactly reproduce the synapse/neuron structure, such as, for example, arrays of spin wave transmitters/receivers, or fixed or mobile magnetic particles, such as skyrmions and domain walls [187]. Micromagnetic simulations with predictive power, coupled with gradient descent, have modeled learning tasks [185]. Experimental demonstrations with these complex physical systems remain to be carried out.…”

Section: Advances In Science and Technology To Meet Challengesmentioning

confidence: 99%

“…Taking full advantage of the dynamical behavior of spintronic devices will require the development of dedicated learning algorithms, inspired by advances in both machine learning and computational neuroscience. The fact that the behavior of spintronic devices relies on purely physical phenomena that can be predictively described and integrated into neural network programming libraries is a key enabler for this task [185].…”

Section: Current and Future Challengesmentioning

confidence: 99%

See 1 more Smart Citation

2022 roadmap on neuromorphic computing and engineering

Christensen

Dittmann

Linares-Barranco

et al. 2022

Neuromorph. Comput. Eng.

392

200

View full text Add to dashboard Cite

Modern computation based on the von Neumann architecture is today a mature cutting-edge science. In the Von Neumann architecture, processing and memory units are implemented as separate blocks interchanging data intensively and continuously. This data transfer is responsible for a large part of the power consumption. The next generation computer technology is expected to solve problems at the exascale with 1018 calculations each second. Even though these future computers will be incredibly powerful, if they are based on von Neumann type architectures, they will consume between 20 and 30 megawatts of power and will not have intrinsic physically built-in capabilities to learn or deal with complex data as our brain does. These needs can be addressed by neuromorphic computing systems which are inspired by the biological concepts of the human brain. This new generation of computers has the potential to be used for the storage and processing of large amounts of digital information with much lower power consumption than conventional processors. Among their potential future applications, an important niche is moving the control from data centers to edge devices. The aim of this Roadmap is to present a snapshot of the present state of neuromorphic technology and provide an opinion on the challenges and opportunities that the future holds in the major areas of neuromorphic technology, namely materials, devices, neuromorphic circuits, neuromorphic algorithms, applications, and ethics. The Roadmap is a collection of perspectives where leading researchers in the neuromorphic community provide their own view about the current state and the future challenges for each research area. We hope that this Roadmap will be a useful resource by providing a concise yet comprehensive introduction to readers outside this field, for those who are just entering the field, as well as providing future perspectives for those who are well established in the neuromorphic computing community.

show abstract

Section: Advances In Science and Technology To Meet Challengesmentioning

confidence: 99%

Section: Current and Future Challengesmentioning

confidence: 99%

2022 roadmap on neuromorphic computing and engineering

Christensen

Dittmann

Linares-Barranco

et al. 2022

Neuromorph. Comput. Eng.

392

200

View full text Add to dashboard Cite

show abstract

“…This includes anisotropic and non-reciprocal dispersion relations as well as tunability. Moreover, there is a growing use of the non-linear interactions of spin waves for advanced computing proposals [3][4][5]; these applications rely on magnetic bodies where large populations of coherently pumped spin waves share a common space with their less coherent biproducts [6,7] and the thermal populations of spin waves [8][9][10]. It is thus of interest to develop experimental techniques able of measuring spin waves in broad frequency intervals with a large dynamic range, ideally from the floor of the thermal population of spin waves up to the regime of large amplitudes of magnetization precession.…”

Section: Introductionmentioning

confidence: 99%

Measuring a population of spin waves from the electrical noise of an inductively coupled antenna

Devolder,

Ngom,

Mouhoub

et al. 2022

Preprint

View full text Add to dashboard Cite

We study how a population of spin waves can be characterized from the analysis of the electrical microwave noise delivered by an inductive antenna placed in its vicinity. The measurements are conducted on a synthetic antiferromagnetic thin stripe covered by a micron-sized antenna that feeds a spectrum analyser after amplification. The antenna noise contains two contributions. The population of incoherent spin waves generates a fluctuating field that is sensed by the antenna: this is the "magnon noise". The antenna noise also contains the contribution of the electronic fluctuations: the Johnson-Nyquist noise. The latter depends on all impedances within the measurement circuit; this includes the antenna self-inductance. As a result, the electronic noise contains information about the magnetic susceptibility, though it does not inform on the absolute amplitude of the magnetic fluctuations. For micrometer-sized systems at thermal equilibrium, the electronic noise dominates and the pure magnon noise cannot be determined. If in contrast the spinwave bath is not at thermal equilibrium with the measurement circuit, and if the spinwave population can be changed then one could measure a mode-resolved effective magnon temperature provided specific precautions are implemented.

show abstract

“…simplify the design structure of wave-based logic gates 6,11,12,13 . Furthermore, the nanoscale wavelength and pronounced nonlinear phenomena of spin-waves are unique comparing to the acoustic waves and microwaves 14,15,16,17 that makes them promising for the nanoscale Boolean/non-Boolean computing 18,19,20,21 .…”

Section: Introductionmentioning

confidence: 99%

Numerical model for 32-bit magnonic ripple carry adder

Garlando¹,

Wang²,

Dobrovolskiy³

et al. 2021

Preprint

View full text Add to dashboard Cite

In CMOS-based electronics, the most straightforward way to implement a summation operation is to use the ripple carry adder (RCA). Magnonics, the field of science concerned with data processing by spin-waves and their quanta magnons, recently proposed a magnonic half-adder that can be considered as the simplest magnonic integrated circuit. Here, we develop a computation model for the magnonic basic blocks to enable the design and simulation of magnonic gates and magnonic circuits of arbitrary complexity and demonstrate its functionality on the example of a 32-bit integrated RCA. It is shown that the RCA requires the utilization of additional regenerators based on magnonic directional couplers with embedded amplifiers to normalize the magnon signals in-between the half-adders. The benchmarking of large-scale magnonic integrated circuits is performed. The energy consumption of 30 nm-based magnonic 32-bit adder can be as low as 961 aJ per operation with taking into account all required amplifiers.

show abstract

Nanoscale neural network using non-linear spin-wave interference

Cited by 8 publications

References 20 publications

2022 roadmap on neuromorphic computing and engineering

2022 roadmap on neuromorphic computing and engineering

Measuring a population of spin waves from the electrical noise of an inductively coupled antenna

Numerical model for 32-bit magnonic ripple carry adder

Contact Info

Product

Resources

About