Related papers: Multi-state MRAM cells for hardware neuromorphic c…
A new spintronic nonvolatile memory cell analogous to 1T DRAM with non-destructive read is proposed. The cells can be used as neural computing units. A dual-circuit neural network architecture is proposed to leverage these devices against…
We propose an all-electric implementation of a precessionally switched perpendicular magnetic anisotropy magneto-tunneling-junction (p-MTJ) based toggle memory cell where data is written with voltage-controlled-magnetic-anisotropy (VCMA)…
Physical devices exhibiting stochastic functions with low energy consumption and high device density have the potential to enable complex probability-based computing algorithms, accelerate machine learning tasks, and enhance hardware…
The ever-increasing amount of data from ubiquitous smart devices fosters data-centric and cognitive algorithms. Traditional digital computer systems have separate logic and memory units, resulting in a huge delay and energy cost for…
A multi-bit digital weight cell for high-performance, inference-only non-GPU-like neuromorphic accelerators is presented. The cell is designed with simplicity of peripheral circuitry in mind. Non-volatile storage of weights which eliminates…
This paper introduces an analog-to-stochastic converter using a magnetic tunnel junction (MTJ) device for vision chips based on stochastic computation. Stochastic computation has been recently exploited for area-efficient hardware…
Future mobile devices are anticipated to perceive, understand and react to the world on their own by running multiple correlated deep neural networks on-device. Yet the complexity of these neural networks needs to be trimmed down both…
In this paper, we propose a novel memory-centric scheme based on CMOS SRAM for acceleration of data intensive applications. Our proposal aims at dynamically increasing the on-chip memory storage capacity of SRAM arrays on-demand. The…
Magnetic tunnel junctions (MTJs) interconnected via a continuous ferromagnetic free layer were fabricated for Spin Torque Majority Gate (STMG) logic. The MTJs are biased independently and show magnetoelectric response under spin transfer…
Deep Spiking Neural Networks are becoming increasingly powerful tools for cognitive computing platforms. However, most of the existing literature on such computing models are developed with limited insights on the underlying hardware…
Spin transfer torque magnetic random access memory (STT-MRAM) is a promising candidate for next generation memory as it is non-volatile, fast, and has unlimited endurance. Another important aspect of STT-MRAM is that its core component, the…
We comment on both recent progress and lingering puzzles related to research on magnetic tunnel junctions (MTJs). MTJs are already being used in applications such as magnetic-field sensors in the read heads of disk drives, and they may also…
Smart material implication (SIMPLY) logic has been recently proposed for the design of energy-efficient Logic-in-Memory (LIM) architectures based on non-volatile resistive memory devices. The SIMPLY logic is enabled by adding a comparator…
CMOS-compatible HfO2-based ferroelectric tunnel junction (FTJ) has attracted significant attention as a promising candidate for in-memory computing (IMC) due to its extremely low power consumption. However, conventional FTJs face inherent…
Two promising strategies for achieving efficient control of magnetization in future magnetic memory and non-volatile spin logic devices are spin transfer torque from spin polarized currents and voltage-controlled magnetic anisotropy (VCMA).…
We demonstrate that thermally stable perpendicular magnetic tunnel junctions (pMTJs), widely used in spin-transfer torque magnetic random-access memory, can be actuated with nanosecond pulses to exhibit tunable stochastic behavior. This…
In late fusion, each modality is processed in a separate unimodal Convolutional Neural Network (CNN) stream and the scores of each modality are fused at the end. Due to its simplicity late fusion is still the predominant approach in many…
Neural networks powered with external memory simulate computer behaviors. These models, which use the memory to store data for a neural controller, can learn algorithms and other complex tasks. In this paper, we introduce a new memory to…
The role of universal memory can be successfully satisfied by magnetic tunnel junctions (MTJs) where the writing mechanism is based on spin-transfer torque (STT). An improvement in the switching properties (lower switching current density…
Magnetic tunnel junctions (MTJs) are basic building blocks for devices such as magnetic random access memories (MRAMs). The relevance for modern computation of non-volatile high-frequency memories makes ac-transport measurements of MTJs…