Can we open the black box of AI?
Можем ли мы открыть «чёрный ящик» ИИ?
2016-10-01
SCID: 54.1/ntpqbep3
Discuss with AI
artificial intelligenceexplainabilityinterpretabilitymachine learning
Figures from the paper
Abstract (AI)
Artificial intelligence is everywhere. But before scientists trust it, they first need to understand how machines learn.
Key Findings
1
The paper addresses the problem of opening the 'black box' of artificial intelligence to improve interpretability.
2
Understanding how machines learn is necessary before scientists can trust AI.
Research Object
Artificial intelligence (AI) systems / machine learning models
Research Subject
Interpreting and understanding how AI systems learn (opening the 'black box' of model learning and decision processes)
Publication Details
Publication Date
2016-10-01
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest