Advanced search
1 file | 2.69 MB Add to list
Author
Organization
Abstract
An augmented appraisal degree (AAD) has been conceived as a mathematical representation of the connotative meaning in an experience-based evaluation, which depends on a particular experience or knowledge. Aiming to improve the interpretability of computer predictions, we explore the use of AADs to represent evaluations that are per- formed by a machine to predict the class of a particular object. Hence, we propose a novel method whereby predictions made using a support vector machine classification process are augmented through AADs. An illustra- tive example, in which the classes of handwritten digits are predicted, shows how the augmentation of such predictions can favor their interpretability.
Keywords
Explainable artificial intelligence, Augmented appraisal degrees, Augmented fuzzy sets, Support vector machines

Downloads

  • EUSFLAT 2019 paper 30.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 2.69 MB

Citation

Please use this url to cite or link to this publication:

MLA
Loor Romero, Marcelo Eduardo, and Guy De Tré. “Explaining Computer Predictions with Augmented Appraisal Degrees.” Proceedings of the 11th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT 2019), vol. 1, Atlantis, 2019, pp. 158–65.
APA
Loor Romero, M. E., & De Tré, G. (2019). Explaining computer predictions with augmented appraisal degrees. In Proceedings of the 11th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT 2019) (Vol. 1, pp. 158–165). Prague, Czech Republic: Atlantis.
Chicago author-date
Loor Romero, Marcelo Eduardo, and Guy De Tré. 2019. “Explaining Computer Predictions with Augmented Appraisal Degrees.” In Proceedings of the 11th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT 2019), 1:158–65. Atlantis.
Chicago author-date (all authors)
Loor Romero, Marcelo Eduardo, and Guy De Tré. 2019. “Explaining Computer Predictions with Augmented Appraisal Degrees.” In Proceedings of the 11th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT 2019), 1:158–165. Atlantis.
Vancouver
1.
Loor Romero ME, De Tré G. Explaining computer predictions with augmented appraisal degrees. In: Proceedings of the 11th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT 2019). Atlantis; 2019. p. 158–65.
IEEE
[1]
M. E. Loor Romero and G. De Tré, “Explaining computer predictions with augmented appraisal degrees,” in Proceedings of the 11th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT 2019), Prague, Czech Republic, 2019, vol. 1, pp. 158–165.
@inproceedings{8628882,
  abstract     = {An augmented appraisal degree (AAD) has been conceived as a mathematical representation of the connotative meaning in an experience-based evaluation, which depends on a particular experience or knowledge. Aiming to improve the interpretability of computer predictions, we explore the use of AADs to represent evaluations that are per- formed by a machine to predict the class of a particular object. Hence, we propose a novel method whereby predictions made using a support vector machine classification process are augmented through AADs. An illustra- tive example, in which the classes of handwritten digits are predicted, shows how the augmentation of such predictions can favor their interpretability.},
  author       = {Loor Romero, Marcelo Eduardo and De Tré, Guy},
  booktitle    = {Proceedings of the 11th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT 2019)},
  isbn         = {9789462527706},
  issn         = {2589-6644},
  keywords     = {Explainable artificial intelligence,Augmented appraisal degrees,Augmented fuzzy sets,Support vector machines},
  language     = {eng},
  location     = {Prague, Czech Republic},
  pages        = {158--165},
  publisher    = {Atlantis},
  title        = {Explaining computer predictions with augmented appraisal degrees},
  url          = {http://dx.doi.org/10.2991/eusflat-19.2019.24},
  volume       = {1},
  year         = {2019},
}

Altmetric
View in Altmetric