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.
| Original language | English (US) |
|---|---|
| Title of host publication | 2024 IEEE 6th International Conference on AI Circuits and Systems, AICAS 2024 - Proceedings |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 129-133 |
| Number of pages | 5 |
| ISBN (Electronic) | 9798350383638 |
| DOIs | |
| State | Published - 2024 |
| Event | 6th IEEE International Conference on AI Circuits and Systems, AICAS 2024 - Abu Dhabi, United Arab Emirates Duration: Apr 22 2024 → Apr 25 2024 |
Publication series
| Name | 2024 IEEE 6th International Conference on AI Circuits and Systems, AICAS 2024 - Proceedings |
|---|
Conference
| Conference | 6th IEEE International Conference on AI Circuits and Systems, AICAS 2024 |
|---|---|
| Country/Territory | United Arab Emirates |
| City | Abu Dhabi |
| Period | 04/22/24 → 04/25/24 |
Bibliographical note
Publisher Copyright:© 2024 IEEE.
Keywords
- clustering
- deep neural networks
- interpretability
- singular value decomposition
- trustworthiness
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Vision and Pattern Recognition
- Hardware and Architecture
- Electrical and Electronic Engineering
- Instrumentation