2023
DOI: 10.1007/978-3-031-27181-6_1
|View full text |Cite
|
Sign up to set email alerts
|

The PSyKE Technology for Trustworthy Artificial Intelligence

Abstract: Transparency is one of the "Ethical Principles in the Context of AI Systems" as described in the Ethics Guidelines for Trustworthy Artificial Intelligence (TAI). It is closely linked to four other principles -respect for human autonomy, prevention of harm, traceability and explainability -and involves numerous ways in which opaqueness can have undesirable impacts, such as discrimination, inequality, segregation, marginalisation, and manipulation. The opaqueness of many AI tools and the inability to understand … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
3
3
1

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(3 citation statements)
references
References 20 publications
0
3
0
Order By: Relevance
“…The effectiveness of the FiRe score in evaluating and comparing the quality of SKE techniques' extracted knowledge has been assessed by running several experiments. The PSYKE framework 1 [7,27,28,30] has been used to train a BB predictor and a set of extractors on the well-known Iris data set 2 [12]. Using a simple data set allows easy depiction of decision boundaries and facilitates visual comparisons of resulting knowledge.…”
Section: Experiments and Discussionmentioning
confidence: 99%
“…The effectiveness of the FiRe score in evaluating and comparing the quality of SKE techniques' extracted knowledge has been assessed by running several experiments. The PSYKE framework 1 [7,27,28,30] has been used to train a BB predictor and a set of extractors on the well-known Iris data set 2 [12]. Using a simple data set allows easy depiction of decision boundaries and facilitates visual comparisons of resulting knowledge.…”
Section: Experiments and Discussionmentioning
confidence: 99%
“…The PSyKE [8,29,30,32] software library is a Python framework providing general-purpose support to SKE. It can be exploited to obtain logic rules from BB classifiers and regressors via several pedagogical extraction methods.…”
Section: Psykementioning
confidence: 99%
“…the methods used to partition the input space, approximate black-box decisions, and construct the extracted symbolic knowledge. Finally, to demonstrate the versatility of hypercube-based methods, we analyse disparate SKE scenarios via the PSyKE framework [8,29,30,32]-that is, a platform combining SKE and Semantic Web to provide human-interpretability and intelligent agent-interoperability for BB-based machine learning tasks.…”
Section: Introductionmentioning
confidence: 99%