On the Opacity of Deep Neural Networks
Research output: Contribution to journal › Journal article › Research › peer-review
Deep neural networks are said to be opaque, impeding the development of safe and trustworthy artificial intelligence, but where this opacity stems from is less clear. What are the sufficient properties for neural network opacity? Here, I discuss five common properties of deep neural networks and two different kinds of opacity. Which of these properties are sufficient for what type of opacity? I show how each kind of opacity stems from only one of these five properties, and then discuss to what extent the two kinds of opacity can be mitigated by explainability methods.
Original language | English |
---|---|
Journal | Canadian Journal of Philosophy |
ISSN | 0045-5091 |
DOIs | |
Publication status | E-pub ahead of print - 2024 |
Bibliographical note
Publisher Copyright:
© The Author(s), 2024. Published by Cambridge University Press on behalf of The Canadian Journal of Philosophy Inc.
- deep neural networks, explainability, mitigation, model size, opacity
Research areas
ID: 389904615