paper-with-me

홈 › Papers

Plasticity-Enhanced Domain-Wall MTJ Neural Networks for Energy-Efficient Online Learning

2020-03-04 · Christopher H. Bennett, T. Patrick Xiao, Can Cui, Naimul Hassan, Otitoaleke G. Akinola, Jean Anne C. Incorvia, Alvaro Velasquez, Joseph S. Friedman, Matthew J. Marinella

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 consists of unsupervised (clustering) as well as supervised sub-systems, and generalizes quickly (with few samples). We demonstrate interactions between physical properties of this device and optimal implementation of neuroscience-inspired plasticity learning rules, and highlight performance on a suite of tasks. Our energy analysis confirms the value of the approach, as the learning budget stays below 20 $\mu J$ even for large tasks used typically in machine learning.

📄 PDF Abstract BibTeX arXiv:2003.02357

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningClustering

Similar Papers 제목 키워드 기반

Uncovering wall-shear stress dynamics from neural-network enhanced fluid flow measurements

2023-10-17 · Esther Lagemann, Steven L. Brunton, Christian Lagemann

Friction drag from a turbulent fluid moving past or inside an object plays a crucial role in domains as diverse as transportation, public utility infrastructure, energy technology, and human health. As a direct measure o…

FrictionOptical Flow Estimation

Free-Energy-Gated Plasticity for Real-Time Online Motor Learning in Physical Human--Robot Interaction

2026-08-24 · Hiroki Sawada, Jun Tani arxiv

Fully online embodied learning requires synaptic adaptation to acquire new behaviors while preserving previously learned dynamics during ongoing interaction. We extend the Predictive-Coding-inspired Variational Recurrent…

Balancing Stability and Plasticity in Pretrained Detector: A Dual-Path Framework for Incremental Object Detection

2025-04-14 · Songze Li, Qixing Xu, Tonghua Su, Xu-Yao Zhang 외

The balance between stability and plasticity remains a fundamental challenge in pretrained model-based incremental object detection (PTMIOD). While existing PTMIOD methods demonstrate strong performance on in-domain task…

Domain Adaptationobject-detectionObject Detectionparameter-efficient fine-tuning

EchoSpike Predictive Plasticity: An Online Local Learning Rule for Spiking Neural Networks

2024-05-22 · Lars Graf, Zhe Su, Giacomo Indiveri

The drive to develop artificial neural networks that efficiently utilize resources has generated significant interest in bio-inspired Spiking Neural Networks (SNNs). These networks are particularly attractive due to thei…

Self-Supervised Learning

Image Synthesis Using Spintronic Deep Convolutional Generative Adversarial Network

2026-01-04 · Saumya Gupta, Abhinandan, Venkatesh vadde, Bhaskaran Muralidharan 외 arxiv

The computational requirements of generative adversarial networks (GANs) exceed the limit of conventional Von Neumann architectures, necessitating energy efficient alternatives such as neuromorphic spintronics. This work…

Image Generation