Please use this identifier to cite or link to this item:
|Publication type:||Conference paper|
|Type of review:||Peer review (abstract)|
|Title:||Two to trust : AutoML for safe modelling and interpretable deep learning for robustness|
Satyawan, Yvan Putra
|Proceedings:||Postproceedings of the 1st TAILOR Workshop on Trustworthy AI at ECAI 2020|
|Conference details:||1st TAILOR Workshop on Trustworthy AI at ECAI 2020, Santiago de Compostela, Spain, 29-30 August 2020|
|Publisher / Ed. Institution:||Springer|
|Subjects:||Automated deep learning; AutoDL; Adversarial attacks|
|Subject (DDC):||006: Special computer methods|
|Abstract:||With great power comes great responsibility. The success of machine learning, especially deep learning, in research and practice has attracted a great deal of interest, which in turn necessitates increased trust. Sources of mistrust include matters of model genesis ("Is this really the appropriate model?") and interpretability ("Why did the model come to this conclusion?", "Is the model safe from being easily fooled by adversaries?"). In this paper, two partners for the trustworthiness tango are presented: recent advances and ideas, as well as practical applications in industry in (a) Automated machine learning (AutoML), a powerful tool to optimize deep neural network architectures and netune hyperparameters, which promises to build models in a safer and more comprehensive way; (b) Interpretability of neural network outputs, which addresses the vital question regarding the reasoning behind model predictions and provides insights to improve robustness against adversarial attacks.|
|Fulltext version:||Accepted version|
|License (according to publishing contract):||Licence according to publishing contract|
|Departement:||School of Engineering|
|Organisational Unit:||Institute of Applied Information Technology (InIT)|
|Published as part of the ZHAW project:||Ada – Advanced Algorithms for an Artificial Data Analyst|
QualitAI - Quality control of industrial products via deep learning on images
|Appears in collections:||Publikationen School of Engineering|
Files in This Item:
|2021_Amirian_etal_AutoML-for-safe-modelling_TAILOR_ECAI.pdf||2.89 MB||Adobe PDF|
Show full item record
Amirian, M., Tuggener, L., Chavarriaga, R., Satyawan, Y. P., Schilling, F.-P., Schwenker, F., & Stadelmann, T. (2021, March). Two to trust : AutoML for safe modelling and interpretable deep learning for robustness. Postproceedings of the 1st TAILOR Workshop on Trustworthy AI at ECAI 2020. https://doi.org/10.21256/zhaw-22061
Amirian, M. et al. (2021) ‘Two to trust : AutoML for safe modelling and interpretable deep learning for robustness’, in Postproceedings of the 1st TAILOR Workshop on Trustworthy AI at ECAI 2020. Springer. Available at: https://doi.org/10.21256/zhaw-22061.
M. Amirian et al., “Two to trust : AutoML for safe modelling and interpretable deep learning for robustness,” in Postproceedings of the 1st TAILOR Workshop on Trustworthy AI at ECAI 2020, Mar. 2021. doi: 10.21256/zhaw-22061.
Amirian, Mohammadreza, et al. “Two to Trust : AutoML for Safe Modelling and Interpretable Deep Learning for Robustness.” Postproceedings of the 1st TAILOR Workshop on Trustworthy AI at ECAI 2020, Springer, 2021, https://doi.org/10.21256/zhaw-22061.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.