arXiv 2308.058102026-07-03cs.CV

自旋电子学用于图像识别：通过数据驱动模拟进行性能基准测试

Spintronics for image recognition: performance benchmarking via data-driven simulations

Institute of Condensed Matter and Nanosciences, Université catholique de Louvain（比利时列日大学凝聚态与纳米科学研究所）；Univ. Grenoble Alpes, CEA, CNRS, Grenoble INP, SPINTEC（格勒诺布尔阿尔卑斯大学、CEA、CNRS、格勒诺布尔INP、SPINTEC）；Institute for Information and Communication Technologies, Electronics and Applied Mathematics, Université catholique de Louvain（比利时列日大学信息与通信技术、电子与应用数学研究所）

Anatole Moureaux, Chloé Chopin, Simon de Wergifosse, Laurent Jacques, Flavio Abreu Araujo

备注：: 15 pages, 5 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

基于数据驱动Thiele方程模拟的磁隧道结自旋扭矩振荡器作为极端学习机的非线性源，在MNIST等数据集上实现图像分类，性能与ReLU和sigmoid相当。

摘要：

我们展示了一种基于时间延迟的模拟磁隧道结（MTJ）的极端学习机（ELM）用于图像分类的演示。由于MTJ的基态是磁涡旋，我们将其称为基于涡旋的自旋扭矩振荡器（STVO）。磁涡旋的动力学通过称为数据驱动Thiele方程方法（DD-TEA）的模型进行模拟。这避免了与重复实验操作相关的约束，用于超参数搜索和基准测试。我们通过在MNIST、EMNIST-letters和Fashion MNIST数据集上成功进行分类任务，展示了我们实现的多样性。通过模拟，我们表明在具有足够数量参数的ELM中，使用STVO动力学作为非线性源所达到的性能与使用经典软件激活函数（如ReLU和sigmoid）所获得的性能相当。虽然在MNIST数据集上达到了最先进的准确率水平，但由于网络架构的简单性和数据复杂性的增加，我们的模型在EMNIST-letters和Fashion MNIST上的性能较低。我们期望DD-TEA框架将能够探索更深入、更复杂的基于STVO的架构，最终提高分类精度。

英文摘要：

We present a demonstration of image classification using an extreme learning machine (ELM) based on a unique simulated magnetic tunnel junction (MTJ) delayed in time. As the ground state of the MTJ is a magnetic vortex, we refer to it as a vortex-based spin-torque oscillator (STVO). The dynamics of the magnetic vortex is simulated with a model called the data-driven Thiele equation approach (DD-TEA). This allows to avoid the constraints associated with repeated experimental manipulation for hyperparameters search and benchmarking. We showcase the versatility of our implementation by using it successfully for classification tasks on the MNIST, EMNIST-letters and Fashion MNIST datasets. Through simulations, we show that within an ELM with a sufficient number of parameters, the performance reached using the STVO dynamics as a source of nonlinearity is equivalent to the ones obtained with classical software activation functions such as the reLU and the sigmoid. While achieving state-of-the-art accuracy levels on the MNIST dataset, our model's performance on EMNIST-letters and Fashion MNIST is lower due to the simplicity of the network architecture and the increased complexity of the data. We expect that the DD-TEA framework will enable the exploration of deeper and more complex STVO-based architectures, ultimately leading to improved classification accuracy.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。