@inproceedings{561b2c51315a44e7b0668c500eeee1ac,
title = "SVD-based Peephole and Clustering to Enhance Trustworthiness in DNN Classifiers",
abstract = "Deep Neural Networks have demonstrated impressive capabilities across various domains, yet their inherent complexity often obscures the rationale behind their predictions. This opacity poses challenges in domains where explainability is critical. Here, we present a novel methodology inspired by signal processing that leverages Singular Value Decomposition to both remove the redundancy in the neural network and derive compressed feature representations to be analyzed with clustering. We carried out empirical experiments with a network of the VGG family trained on CIFAR-10 and FMNIST datasets, and propose two strategies to address the trustworthiness issue in AI decisions.",
keywords = "clustering, deep neural networks, interpretability, singular value decomposition, trustworthiness",
author = "Livia Manovi and Lorenzo Capelli and Alex Marchioni and Filippo Martinini and Gianluca Setti and Mauro Mangia and Riccardo Rovatti",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 6th IEEE International Conference on AI Circuits and Systems, AICAS 2024 ; Conference date: 22-04-2024 Through 25-04-2024",
year = "2024",
doi = "10.1109/AICAS59952.2024.10595919",
language = "English (US)",
series = "2024 IEEE 6th International Conference on AI Circuits and Systems, AICAS 2024 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "129--133",
booktitle = "2024 IEEE 6th International Conference on AI Circuits and Systems, AICAS 2024 - Proceedings",
address = "United States",
}