On the Readability of Deep Learning Models: the role of Kernel-based Deep Architectures
Deep Neural Networks achieve state-of-the-art performances in several semantic NLP tasks but lack of explanation capabilities as for the limited interpretability of the underlying acquired models. In other words, tracing back causal connections between the linguistic properties of an input instance...
Na minha lista:
| Principais autores: | , , |
|---|---|
| Format: | Chapter |
| Sprog: | Inglês |
| Udgivet: |
Accademia University Press
2018
|
| Online adgang: | https://doi.org/10.4000/books.aaccademia.3250 https://hdl.handle.net/20.500.13089/1daj https://books.openedition.org/aaccademia/3250 |
| Tags: |
Ingen Tags, Vær først til at tagge denne postø!
|