⌕ Поиск по атласу

NIST · ИТ · 33edbbf6a283e8e704ad

33edbbf6a283e8e704ad · Gradient Decomposition Methods for Training Neural Networks with Non-Ideal Synaptic Devices

Gradient Decomposition Methods for Training Neural Networks with Non-Ideal Synaptic Devices

While promising for high capacity machine learning accelerators, memristor devices have non-idealities that prevent software-equivalent accuracies when used for online training. This work uses a combination of Mini-Batch Gradient Descent (MBGD) to average

Официальный источник · 2021-11-22

Полные импортированные сведения карточки
{
  "title_en": "Gradient Decomposition Methods for Training Neural Networks with Non-Ideal Synaptic Devices",
  "designation": "",
  "series": "",
  "status": "",
  "date": "2021-11-22",
  "date_original": "November 22, 2021",
  "url": "https://www.nist.gov/publications/gradient-decomposition-methods-training-neural-networks-non-ideal-synaptic-devices",
  "source": "NIST Publications",
  "display_en": "",
  "authors_en": "Junyun Zhao, Siyuan Huang, Osama Yousuf, Yutong Gao, Brian Hoskins , Gina Adam",
  "abstract_excerpt_en": "While promising for high capacity machine learning accelerators, memristor devices have non-idealities that prevent software-equivalent accuracies when used for online training. This work uses a combination of Mini-Batch Gradient Descent (MBGD) to average",
  "id": "33edbbf6a283e8e704ad",
  "sources": [
    "NIST Publications"
  ],
  "source_records": [
    {
      "title_en": "Gradient Decomposition Methods for Training Neural Networks with Non-Ideal Synaptic Devices",
      "designation": "",
      "series": "",
      "status": "",
      "date": "2021-11-22",
      "date_original": "November 22, 2021",
      "url": "https://www.nist.gov/publications/gradient-decomposition-methods-training-neural-networks-non-ideal-synaptic-devices",
      "source": "NIST Publications",
      "display_en": "",
      "authors_en": "Junyun Zhao, Siyuan Huang, Osama Yousuf, Yutong Gao, Brian Hoskins , Gina Adam",
      "abstract_excerpt_en": "While promising for high capacity machine learning accelerators, memristor devices have non-idealities that prevent software-equivalent accuracies when used for online training. This work uses a combination of Mini-Batch Gradient Descent (MBGD) to average"
    }
  ],
  "translation_state": "none"
}