Minds and Machines 32 (1):135-158 (2022)

Authors
Abstract
As AI systems become increasingly complex it may become unclear, even to the designer of a system, why exactly a system does what it does. This leads to a lack of trust in AI systems. To solve this, the field of explainable AI has been working on ways to produce explanations of these systems’ behaviors. Many methods in explainable AI, such as LIME, offer only a statistical argument for the validity of their explanations. However, some methods instead study the internal structure of the system and try to find components which can be assigned an interpretation. I believe that these methods provide more valuable explanations than those statistical in nature. I will try to identify which explanations can be considered internal to the system using the Chomskyan notion of tacit knowledge. I argue that each explanation expresses a rule, and through the localization of this rule in the system internals, we can take a system to have tacit knowledge of the rule. I conclude that the only methods which are able to sufficiently establish this tacit knowledge are those along the lines of Olah : 4901–4911, 2017), and therefore they provide explanations with unique strengths.
Keywords No keywords specified (fix it)
Categories (categorize this paper)
ISBN(s)
DOI 10.1007/s11023-021-09588-1
Options
Edit this record
Mark as duplicate
Export citation
Find it on Scholar
Request removal from index
Translate to english
Revision history

Download options

PhilArchive copy


Upload a copy of this paper     Check publisher's policy     Papers currently archived: 70,163
External links

Setup an account with your affiliations in order to access resources via your University's proxy server
Configure custom proxy (use this if your affiliation does not provide a proxy)
Through your library

References found in this work BETA

Aspects of the Theory of Syntax.Noam Chomsky - 1965 - Cambridge, MA, USA: MIT Press.
On the Proper Treatment of Connectionism.Paul Smolensky - 1988 - Behavioral and Brain Sciences 11 (1):1-23.

View all 18 references / Add more references

Citations of this work BETA

No citations found.

Add more citations

Similar books and articles

Taking the Collective Out of Tacit Knowledge.Stephen Turner - 2013 - Philosophia Scientae 17:75-92.
Taking the Collective Out of Tacit Knowledge.Stephen P. Turner - 2013 - Philosophia Scientiae 17 (3):75-92.
Tacit Knowledge Meets Analytic Kantianism.Stephen Turner - 2014 - Tradition and Discovery 41 (1):33-47.
Non-Human Knowledge According to Michael Polanyi.Mihály Héder & Daniel Paksi - 2018 - Tradition and Discovery 44 (1):50-66.
Analysing Tacit Knowledge: Response to Henry and Lowney.Harry Collins - 2011 - Tradition and Discovery 38 (1):38-42.
Inferentialism and Tacit Knowledge.Jon Cogburn - 2004 - Behavior and Philosophy 32 (2):503 - 524.
At the Margins of Tacit Knowledge.Michael Lynch - 2013 - Philosophia Scientiae 17 (3):55-73.
When Tacit is Not Tacit Enough: A Heideggerian Critique of Collins’ “Tacit” Knowledge.Ben Trubody - 2013 - Meta: Research in Hermeneutics, Phenomenology, and Practical Philosophy 5 (2):315-335.

Analytics

Added to PP index
2022-01-12

Total views
25 ( #455,699 of 2,506,521 )

Recent downloads (6 months)
25 ( #35,839 of 2,506,521 )

How can I increase my downloads?

Downloads

My notes