NIST · ИТ · a40ed836fca861ce7710
Combinatorial Methods for Explainable AI
This paper introduces an approach to producing explanations or justifications of decisions made by artificial intelligence and machine learning (AI/ML) systems, using methods derived from fault location in combinatorial testing. We use a conceptually
NIST · ИТОфициальный источник · 2020-10-24
{
"title_en": "Combinatorial Methods for Explainable AI",
"designation": "",
"series": "",
"status": "",
"date": "2020-10-24",
"date_original": "October 24, 2020",
"url": "https://www.nist.gov/publications/combinatorial-methods-explainable-ai",
"source": "NIST Publications",
"display_en": "",
"authors_en": "David R. Kuhn , Raghu N. Kacker , Yu Lei, Dimitris Simos",
"abstract_excerpt_en": "This paper introduces an approach to producing explanations or justifications of decisions made by artificial intelligence and machine learning (AI/ML) systems, using methods derived from fault location in combinatorial testing. We use a conceptually",
"id": "a40ed836fca861ce7710",
"sources": [
"NIST Publications"
],
"source_records": [
{
"title_en": "Combinatorial Methods for Explainable AI",
"designation": "",
"series": "",
"status": "",
"date": "2020-10-24",
"date_original": "October 24, 2020",
"url": "https://www.nist.gov/publications/combinatorial-methods-explainable-ai",
"source": "NIST Publications",
"display_en": "",
"authors_en": "David R. Kuhn , Raghu N. Kacker , Yu Lei, Dimitris Simos",
"abstract_excerpt_en": "This paper introduces an approach to producing explanations or justifications of decisions made by artificial intelligence and machine learning (AI/ML) systems, using methods derived from fault location in combinatorial testing. We use a conceptually"
}
],
"translation_state": "none",
"possible_title_matches": 1
}