Explainable AI: Using Shapley Value to Explain the Anomaly Detection System Based on Machine Learning Approaches.

Standard

Explainable AI: Using Shapley Value to Explain the Anomaly Detection System Based on Machine Learning Approaches. / Zou, Jinying.

в: ПРОЦЕССЫ УПРАВЛЕНИЯ И УСТОЙЧИВОСТЬ, Том 7, № 1, 2020, стр. 355-360.

Результаты исследований: Научные публикации в периодических изданиях › статья

BibTeX

@article{14f11e32167d4430b96f589e1a01a5ec,

title = "Explainable AI: Using Shapley Value to Explain the Anomaly Detection System Based on Machine Learning Approaches.",

abstract = "Recently, deep learning has largely promoted the rapid development of artificial intelligence, and Explainable AI has become a new topic in AI field. For machine learning, especially deep learning, explainable AI is a big challenge. Deep neural networks are a black box for us all. AI algorithms usually cannot explain the logic of each decision when providing a solution. Such opaque decisions cannot be convinced, especially in the fields of military, medical and financial security.Anomaly detection refers to the problem of finding anomaly in dataset. As we know,AI algorithms usually cannot explain the logic of each decision when providing a solution. Such opaque decisions cannot be convinced, especially in the fields of military, medical and financial security.Thus, in this paper we consider using Shapley value to explain the decision tree algorithms in machine learning",

keywords = "anomaly detection, decision tree, explainable AI, Shapley value, anomaly detection, decision tree, explainable AI, Shapley value",

author = "Jinying Zou",

year = "2020",

language = "English",

volume = "7",

pages = "355--360",

journal = "Процессы управления и устойчивость",

issn = "2313-7304",

publisher = "Смирнов Николай Васильевич",

number = "1",

}

RIS

TY - JOUR

T1 - Explainable AI: Using Shapley Value to Explain the Anomaly Detection System Based on Machine Learning Approaches.

AU - Zou, Jinying

PY - 2020

Y1 - 2020

N2 - Recently, deep learning has largely promoted the rapid development of artificial intelligence, and Explainable AI has become a new topic in AI field. For machine learning, especially deep learning, explainable AI is a big challenge. Deep neural networks are a black box for us all. AI algorithms usually cannot explain the logic of each decision when providing a solution. Such opaque decisions cannot be convinced, especially in the fields of military, medical and financial security.Anomaly detection refers to the problem of finding anomaly in dataset. As we know,AI algorithms usually cannot explain the logic of each decision when providing a solution. Such opaque decisions cannot be convinced, especially in the fields of military, medical and financial security.Thus, in this paper we consider using Shapley value to explain the decision tree algorithms in machine learning

AB - Recently, deep learning has largely promoted the rapid development of artificial intelligence, and Explainable AI has become a new topic in AI field. For machine learning, especially deep learning, explainable AI is a big challenge. Deep neural networks are a black box for us all. AI algorithms usually cannot explain the logic of each decision when providing a solution. Such opaque decisions cannot be convinced, especially in the fields of military, medical and financial security.Anomaly detection refers to the problem of finding anomaly in dataset. As we know,AI algorithms usually cannot explain the logic of each decision when providing a solution. Such opaque decisions cannot be convinced, especially in the fields of military, medical and financial security.Thus, in this paper we consider using Shapley value to explain the decision tree algorithms in machine learning

KW - anomaly detection

KW - decision tree

KW - explainable AI

KW - Shapley value

KW - anomaly detection

KW - decision tree

KW - explainable AI

KW - Shapley value

M3 - Article

VL - 7

SP - 355

EP - 360

JO - Процессы управления и устойчивость

JF - Процессы управления и устойчивость

SN - 2313-7304

IS - 1

ER -

ID: 78596769