Related papers: Spintronic virtual neural network by a voltage con…
This paper presents the design of an associative memory with feedback that is capable of on-line temporal sequence learning. A framework for on-line sequence learning has been proposed, and different sequence learning models have been…
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…
Altermagnets, a newly discovered class of magnets, integrate the advantages of both ferromagnets and antiferromagnets, such as enabling anomalous transport without stray fields and supporting ultrafast spin dynamics, offering exciting…
Convolutional neural networks are state-of-the-art and ubiquitous in modern signal processing and machine vision. Nowadays, hardware solutions based on emerging nanodevices are designed to reduce the power consumption of these networks.…
We experimentally study the dynamical modes excited by current-induced spin-orbit torque and its electrostatic gating effect in a 3-terminal planar nano-gap spin Hall nano-oscillator (SHNO) with a moderate interfacial perpendicular magnetic…
Spiking neural networks aim to emulate the brain's properties to achieve similar parallelism and high-processing power. A caveat of these neural networks is the high computational cost to emulate, while current proposals for analogue…
The concept of low-voltage depletion and accumulation of electron charge in semiconductors, utilized in field-effect transistors (FETs), is one of the cornerstones of current information processing technologies. Spintronics which is based…
Networks of spiking neurons and Winner-Take-All spiking circuits (WTA-SNNs) can detect information encoded in spatio-temporal multi-valued events. These are described by the timing of events of interest, e.g., clicks, as well as by…
A new collective behavior of resonant synchronization is discovered and the ability to retrieve information from brain memory is proposed based on this mechanism. We use modified Kuramoto phase oscillator to simulate the dynamics of a…
A major challenge in spin-based electronics is reducing power consumption for magnetization switching of ferromagnets, which is being implemented by injecting a large spin-polarized current. The alternative approach is to control the…
The bistability of ordered spin states in ferromagnets (FMs) provides the magnetic memory functionality. Traditionally, the macroscopic moment of ordered spins in FMs is utilized to write information on magnetic media by a weak external…
In this paper, we develop an in-memory analog computing (IMAC) architecture realizing both synaptic behavior and activation functions within non-volatile memory arrays. Spin-orbit torque magnetoresistive random-access memory (SOT-MRAM)…
Flexible ferromagnetic rings are spin-chain magnets, in which the magnetic and mechanical subsystems are coupled. The coupling is achieved through the tangentially oriented anisotropy axis. The possibility to operate the mechanics of the…
Machine learning imitates the basic features of biological neural networks to efficiently perform tasks such as pattern recognition. This has been mostly achieved at a software level, and a strong effort is currently being made to mimic…
Complementary metal oxide semiconductor (CMOS) devices display volatile characteristics, and are not well suited for analog applications such as neuromorphic computing. Spintronic devices, on the other hand, exhibit both non-volatile and…
The dynamics of antiferromagnets is a current hot topic in condensed matter physics and spintronics. However, the dynamics of insulating antiferromagnets cannot be excited by an electric current, which is a method usually used to manipulate…
The electric control of magnetic anisotropy has important applications for nonvolatile memory and information processing. By first-principles calculations, we show a large nonvolatile control of magnetic anisotropy in…
The Perpendicular Shape Anisotropy Spin Transfer Torque Magnetic Random Access Memory (PSA-STT-MRAM) is a recent concept proposed to maintain the thermal stability of standard MRAM at small diameters, considering thick vertical pillars as…
An energy-efficient voltage controlled domain wall device for implementing an artificial neuron and synapse is analyzed using micromagnetic modeling in the presence of room temperature thermal noise. By controlling the domain wall motion…
Binary stochastic neurons (BSN's) form an integral part of many machine learning algorithms, motivating the development of hardware accelerators for this complex function. It has been recognized that hardware BSN's can be implemented using…