⌕ Поиск по атласу

NIST · ИТ · 930354bef0a40af2d443

930354bef0a40af2d443 · Gradient Descent in Recurrent Neural Networks with Model-Free Multiplexed Gradient Descent: Toward Temporal On-Chip Neuromorphic Learning

Gradient Descent in Recurrent Neural Networks with Model-Free Multiplexed Gradient Descent: Toward Temporal On-Chip Neuromorphic Learning

The brain implements recurrent neural networks (RNNs) efficiently, and modern computing hardware does not. Although specialized neuromorphic hardware is well suited for recurrent implementations in the inference phase, it does not lend itself to the

Официальный источник · 2025-06-12

Полные импортированные сведения карточки
{
  "title_en": "Gradient Descent in Recurrent Neural Networks with Model-Free Multiplexed Gradient Descent: Toward Temporal On-Chip Neuromorphic Learning",
  "designation": "",
  "series": "",
  "status": "",
  "date": "2025-06-12",
  "date_original": "June 12, 2025",
  "url": "https://www.nist.gov/publications/gradient-descent-recurrent-neural-networks-model-free-multiplexed-gradient-descent",
  "source": "NIST Publications",
  "display_en": "",
  "authors_en": "Ryan O'Loughlin , Nicholas Skuda , Bakhrom Oripov , Sonia Buckley , Adam McCaughan",
  "abstract_excerpt_en": "The brain implements recurrent neural networks (RNNs) efficiently, and modern computing hardware does not. Although specialized neuromorphic hardware is well suited for recurrent implementations in the inference phase, it does not lend itself to the",
  "id": "930354bef0a40af2d443",
  "sources": [
    "NIST Publications"
  ],
  "source_records": [
    {
      "title_en": "Gradient Descent in Recurrent Neural Networks with Model-Free Multiplexed Gradient Descent: Toward Temporal On-Chip Neuromorphic Learning",
      "designation": "",
      "series": "",
      "status": "",
      "date": "2025-06-12",
      "date_original": "June 12, 2025",
      "url": "https://www.nist.gov/publications/gradient-descent-recurrent-neural-networks-model-free-multiplexed-gradient-descent",
      "source": "NIST Publications",
      "display_en": "",
      "authors_en": "Ryan O'Loughlin , Nicholas Skuda , Bakhrom Oripov , Sonia Buckley , Adam McCaughan",
      "abstract_excerpt_en": "The brain implements recurrent neural networks (RNNs) efficiently, and modern computing hardware does not. Although specialized neuromorphic hardware is well suited for recurrent implementations in the inference phase, it does not lend itself to the"
    }
  ],
  "translation_state": "none"
}