Visualizing Invariant Features in Vision Models

Sammani, Fawaz; Joukovsky, Boris; Deligiannis, Nikos

doi:10.1109/dsp58604.2023.10167995

Cited by 1 publication

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to undermining fairness and justice in theory, this also has negative effects on society, such as the amplification of social injustice and institutional discrimination. Therefore, it is essential to make sure that these mechanisms are open and responsible [5].This research promotes [6] the use of interpretable machine learning models into algorithmic decision-making processes as a solution to these problems. In contrast to their intricate, opaque competitors, interpretable models offer a human-understandable picture of the decision-making process.…”

Section: Introductionmentioning

confidence: 99%

Transparency in Algorithmic Decision-making: Interpretable Models for Ethical Accountability

Raja Kumar,

Kalnawat,

Pawar

et al. 2024

E3S Web Conf.

View full text Add to dashboard Cite

Concerns regarding their opacity and potential ethical ramifications have been raised by the spread of algorithmic decisionmaking systems across a variety of fields. By promoting the use of interpretable machine learning models, this research addresses the critical requirement for openness and moral responsibility in these systems. Interpretable models provide a transparent and intelligible depiction of how decisions are made, as opposed to complicated black-box algorithms. Users and stakeholders need this openness in order to understand, verify, and hold accountable the decisions made by these algorithms. Furthermore, interpretability promotes fairness in algorithmic results by making it easier to detect and reduce biases. In this article, we give an overview of the difficulties brought on by algorithmic opacity, highlighting how crucial it is to solve these difficulties in a variety of settings, including those involving healthcare, banking, criminal justice, and more. From linear models to rule-based systems to surrogate models, we give a thorough analysis of interpretable machine learning techniques, highlighting their benefits and drawbacks. We suggest that incorporating interpretable models into the design and use of algorithms can result in a more responsible and moral application of AI in society, ultimately benefiting people and communities while lowering the risks connected to opaque decision-making processes.

show abstract

Section: Introductionmentioning

confidence: 99%