Addressing Regulatory Requirements on Explanations for Automated Decisions with Provenance—A Case Study

Autor: Luc Moreau, Niko Tsakalakis, Trung Dong Huynh, Sophie Stalla-Bourdillon, Ayah Helal

Publikováno v: Huynh, T D, Tsakalakis, N, Helal, A, Stalla-Bourdillon, S & Moreau, L 2021, ' Addressing Regulatory Requirements on Explanations for Automated Decisions with Provenance : A Case Study ', Digital Government: Research and Practice, vol. 2, no. 2, 16e . https://doi.org/10.1145/3436897

AI-based automated decisions are increasingly used as part of new services being deployed to the general public. This approach to building services presents significant potential benefits, such as the reduced speed of execution, increased accuracy, l

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2c501aaaad83e4d5d6be9a776ca1f148
https://doi.org/10.1145/3436897

The dual function of explanations: Why it is useful to compute explanations

Autor: Luc Moreau, Nikolaos Tsakalakis, Laura Carmichael, Ayah Helal, Trung Dong Huynh, Sophie Stalla-Bourdillon

Whilst the legal debate concerning automated decision-making has been focused mainly on whether a ‘right to explanation’ exists in the GDPR, the emergence of ‘explainable Artificial Intelligence’ (XAI) has produced taxonomies for the explanat

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::74df4d1184af22bfe5b465a37ab40b58
https://eprints.soton.ac.uk/446899/

Instance-based classification with Ant Colony Optimization

Autor: Ashraf M. Abdelbar, Khalid M. Salama, Alex A. Freitas, Ayah Helal

Publikováno v: Intelligent Data Analysis. 21:913-944

Instance-based learning (IBL) methods predict the class label of a new instance based directly on the distance between the new unlabeled instance and each labeled instance in the training set, without constructing a classification model in the traini

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::2c365a6ec57e7bcb47ddec6d5f4c67b8
https://doi.org/10.3233/ida-160031

Automatic design of ant-miner mixed attributes for classification rule discovery

Autor: Ayah Helal, Fernando E. B. Otero

Publikováno v: GECCO
Helal, A & Otero, F E B 2017, Automatic design of ant-miner mixed attributes for classification rule discovery . in Proceedings of the Genetic and Evolutionary Computation Conference . GECCO Genetic and Evolutionary Computation Conference, New York, USA, pp. 433-440 . https://doi.org/10.1145/3071178.3071306

Ant-Miner Mixed Attributes (Ant-MinerMA) was inspired and built based on ACOMV. which uses an archive-based pheromone model to cope with mixed attribute types. On the one hand, the use of an archive-based pheromone model improved significantly the ru

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fdc126dd8e7d477aeb19943c909f27d9
https://doi.org/10.1145/3071178.3071306

A Mixed-Attribute Approach in Ant-Miner Classification Rule Discovery Algorithm

Autor: Ayah Helal, Fernando E. B. Otero

Publikováno v: Helal, A & Otero, F E B 2016, A Mixed-Attribute Approach in Ant-Miner Classification Rule Discovery Algorithm . in Genetic and Evolutionary Computation Conference (GECCO 2016) . pp. 13-20 . https://doi.org/10.1145/2908812.2908900
Genetic and Evolutionary Computation Conference (GECCO 2016)
GECCO

In this paper, we introduce Ant-MinerMA to tackle mixed-attribute classification problems. Most classification problems involve continuous, ordinal and categorical attributes. The majority of Ant Colony Optimization (ACO) classification algorithms ha

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c43e97f28789291b138e6be20553cf4b
https://kclpure.kcl.ac.uk/en/publications/65d0547b-6cbc-4fa4-ba3c-92d17b5b0e43