{
  "id": "2106.16043",
  "version": "v1",
  "published": "2021-06-30T13:12:05.000Z",
  "updated": "2021-06-30T13:12:05.000Z",
  "title": "Study of the robustness of neural networks based on spintronic neurons",
  "authors": [
    "Eleonora Raimondo",
    "Anna Giordano",
    "Andrea Grimaldi",
    "Vito Puliafito",
    "Mario Carpentieri",
    "Zhongming Zeng",
    "Riccardo Tomasello",
    "Giovanni Finocchio"
  ],
  "categories": [
    "cond-mat.mes-hall"
  ],
  "abstract": "Spintronic technology is emerging as a direction for the hardware implementation of neurons and synapses of neuromorphic architectures. In particular, a single spintronic device can be used to implement the nonlinear activation function of neurons. Here, we propose how to implement spintronic neurons with a sigmoidal and ReLU-like activation functions. We then perform a numerical experiment showing the robustness of neural networks made by spintronic neurons all having different activation functions to emulate device-to-device variations in a possible hardware implementation of the network. Therefore, we consider a vanilla neural network implemented to recognize the categories of the Mixed National Institute of Standards and Technology database, and we show an average accuracy of 98.87 % in the test dataset which is very close to the 98.89% as obtained for the ideal case (all neurons have the same sigmoid activation function). Similar results are also obtained with neurons having a ReLU-like activation function.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2021-06-30T13:12:05.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "robustness",
      "relu-like activation function",
      "hardware implementation",
      "single spintronic device",
      "nonlinear activation function"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}