Abstract
Deep neural networks have exploded in popularity and different types of networks are used to solve a multitude of complex tasks. One such task is anomaly detection, that a type of deep neural network called auto-encoder has become extremely proficient at solving. The low level neural activity, produced by such a network, generates extremely rich representations of the data, which can be used to extract task specific knowledge. In this paper, we built upon previous work and used co-activation graph analysis to extract knowledge from auto-encoders, that were trained for the specific task of anomaly detection. First, we outlined a method for extracting co-activation graphs from auto-encoders. Then, we performed graph analysis to discover that task specific knowledge from the auto-encoder was being encoded into the co-activation graph, and that the extracted knowledge could be used to reveal the role of individual neurons in the network.
Original language | English |
---|---|
Title of host publication | K-CAP 2021 |
Subtitle of host publication | Proceedings of the 11th Knowledge Capture Conference |
Publisher | Association for Computing Machinery, Inc |
Pages | 65-71 |
Number of pages | 7 |
ISBN (Electronic) | 9781450384575 |
DOIs | |
Publication status | Published - Dec 2021 |
Event | 11th ACM International Conference on Knowledge Capture, K-CAP 2021 - Virtual, Online, United States Duration: 2 Dec 2021 → 3 Dec 2021 |
Conference
Conference | 11th ACM International Conference on Knowledge Capture, K-CAP 2021 |
---|---|
Country/Territory | United States |
City | Virtual, Online |
Period | 2/12/21 → 3/12/21 |
Bibliographical note
Publisher Copyright:© 2021 ACM.
Keywords
- anomaly detection
- auto-encoders
- co-activation graphs