c8c47f4ae4475d92004f · A general approach to fast online training of modern datasets on real neuromorphic systems without backpropagation
A general approach to fast online training of modern datasets on real neuromorphic systems without backpropagation
We present parameter-multiplexed gradient descent (PMGD), a perturbative gradient descent framework designed to easily train emergent neuromorphic hardware platforms. We show its applicability to both analog and digital systems. We demonstrate how to use
{
"title_en": "A general approach to fast online training of modern datasets on real neuromorphic systems without backpropagation",
"designation": "",
"series": "",
"status": "",
"date": "2022-09-07",
"date_original": "September 7, 2022",
"url": "https://www.nist.gov/publications/general-approach-fast-online-training-modern-datasets-real-neuromorphic-systems-without",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Sonia Buckley , Adam McCaughan",
"abstract_excerpt_en": "We present parameter-multiplexed gradient descent (PMGD), a perturbative gradient descent framework designed to easily train emergent neuromorphic hardware platforms. We show its applicability to both analog and digital systems. We demonstrate how to use",
"id": "c8c47f4ae4475d92004f",
"sources": [
"NIST Publications"
],
"source_records": [
{
"title_en": "A general approach to fast online training of modern datasets on real neuromorphic systems without backpropagation",
"designation": "",
"series": "",
"status": "",
"date": "2022-09-07",
"date_original": "September 7, 2022",
"url": "https://www.nist.gov/publications/general-approach-fast-online-training-modern-datasets-real-neuromorphic-systems-without",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Sonia Buckley , Adam McCaughan",
"abstract_excerpt_en": "We present parameter-multiplexed gradient descent (PMGD), a perturbative gradient descent framework designed to easily train emergent neuromorphic hardware platforms. We show its applicability to both analog and digital systems. We demonstrate how to use"
}
],
"translation_state": "none"
}