Can we open the black box of AI?

Можем ли мы открыть «чёрный ящик» ИИ?
Davide Castelvecchi
2016-10-01

artificial intelligenceexplainabilityinterpretabilitymachine learning
Artificial intelligence is everywhere. But before scientists trust it, they first need to understand how machines learn.
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.

Artificial intelligence (AI) systems / machine learning models

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
Access Type
Author Information
Authors
Davide Castelvecchi
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat
Make a presentation
100%