Papers by Daniele Rossini
Auditing Deep Learning processes through Kernel-based Explanatory Models (D19-1)
Copied to clipboard
| Challenge: | Existing nonlinearity of deep learning models can be a major drawback . ethical accountability of such systems is becoming a crucial issue . |
| Approach: | They propose to use Layerwise Relevance Propagation to trace back connections between linguistic properties of input instances and system decisions. |
| Outcome: | The proposed model evaluates the transparency and coherence of analogy-based explanations modeling an audit stage for the system. |