相关论文: Comparing domain wall synapse with other Non Volat…

There are pressing problems with traditional computing, especially for accomplishing data-intensive and real-time tasks, that motivate the development of in-memory computing devices to both store information and perform computation.…

A trend towards energy-efficiency, security and privacy has led to a recent focus on deploying DNNs on microcontrollers. However, limits on compute and memory resources restrict the size and the complexity of the ML models deployable in…

In-memory computing is a promising non-von Neumann approach for making energy-efficient deep learning inference hardware. Crossbar arrays of resistive memory devices can be used to encode the network weights and perform efficient analog…

Micromagnetic simulation is carried out to investigate the current-driven domain wall (DW) in a nanowire with perpendicular magnetic anisotropy (PMA). A stepped nanowire is proposed to pin DW and achieve high information storage capacity…

Non-Boolean computing based on emerging post-CMOS technologies can potentially pave the way for low-power neural computing platforms. However, existing work on such emerging neuromorphic architectures have either focused on solely mimicking…

In the last decade, two revolutionary concepts in nano magnetism emerged from research for storage technologies and advanced information processing. The first suggests the use of magnetic domain walls (DWs) in ferromagnetic nanowires to…

Recently we have shown that an architecture based on resistive processing unit (RPU) devices has potential to achieve significant acceleration in deep neural network (DNN) training compared to today's software-based DNN implementations…

The growing demand for storage, due to big data applications, cannot be met by hard disk drives. Domain wall (DW) memory devices such as racetrack memory offer an alternative route to achieve high capacity storage. In DW memory, control of…

A new device structure for spin transfer torque based magnetic random access memory is proposed for on-chip memory applications. Our device structure exploits spin Hall effect to create a differential memory cell that exhibits fast and…

The rapid advancement of neuromorphic technology aims to address the memory wall challenge inherent in conventional von Neumann architectures. This paper critically examines current digital neuromorphic processors and their strategies to…

Neural networks are an increasingly attractive algorithm for natural language processing and pattern recognition. Deep networks with >50M parameters are made possible by modern GPU clusters operating at <50 pJ per op and more recently,…

Machine learning implements backpropagation via abundant training samples. We demonstrate a multi-stage learning system realized by a promising non-volatile memory device, the domain-wall magnetic tunnel junction (DW-MTJ). The system…

Perpendicularly magnetized materials have attracted tremendous interest due to their high anisotropy, which results in extremely narrow, nano-sized domain walls. As a result, the recently studied current-induced domain wall motion (CIDWM)…

Training of deep neural networks (DNNs) is a computationally intensive task and requires massive volumes of data transfer. Performing these operations with the conventional von Neumann architectures creates unmanageable time and power…

Emerging resistive-crossbar memory (RCM) technology can be promising for computationally-expensive analog pattern-matching tasks. However, the use of CMOS analog-circuits with RCM would result in large power-consumption and poor…

DNN+NeuroSim is an integrated framework to benchmark compute-in-memory (CIM) accelerators for deep neural networks, with hierarchical design options from device-level, to circuit-level and up to algorithm-level. A python wrapper is…

In this work we perform investigations of the competition between domain-wall pinning and attraction by anti-notches and finite device borders. The conditions for optimal geometries, which can attain a stable domain-wall pinning, are…

Wave-based platforms for novel unconventional computing approaches like neuromorphic computing require a well-defined, but adjustable flow of wave information combined with non-volatile data storage elements to implement weights which allow…

Neuromorphic circuits mimic partial functionalities of brain in a bio-inspired information processing sense in order to achieve similar efficiencies as biological systems. While there are common mathematical models for neurons, which can be…

Resistive Random Access Memory (RRAM) is an emerging device for processing-in-memory (PIM) architecture to accelerate convolutional neural network (CNN). However, due to the highly coupled crossbar structure in the RRAM array, it is…