Regional, Lattice and Logical Representations of Neural Networks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912417258143744 |
|---|---|
| author | Preto, Sandro Finger, Marcelo |
| author_facet | Preto, Sandro Finger, Marcelo |
| contents | A possible path to the interpretability of neural networks is to (approximately) represent them in the regional format of piecewise linear functions, where regions of inputs are associated to linear functions computing the network outputs. We present an algorithm for the translation of feedforward neural networks with ReLU activation functions in hidden layers and truncated identity activation functions in the output layer. We also empirically investigate the complexity of regional representations outputted by our method for neural networks with varying sizes. Lattice and logical representations of neural networks are straightforward from regional representations as long as they satisfy a specific property. So we empirically investigate to what extent the translations by our algorithm satisfy such property. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_05834 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Regional, Lattice and Logical Representations of Neural Networks Preto, Sandro Finger, Marcelo Logic in Computer Science Artificial Intelligence Machine Learning A possible path to the interpretability of neural networks is to (approximately) represent them in the regional format of piecewise linear functions, where regions of inputs are associated to linear functions computing the network outputs. We present an algorithm for the translation of feedforward neural networks with ReLU activation functions in hidden layers and truncated identity activation functions in the output layer. We also empirically investigate the complexity of regional representations outputted by our method for neural networks with varying sizes. Lattice and logical representations of neural networks are straightforward from regional representations as long as they satisfy a specific property. So we empirically investigate to what extent the translations by our algorithm satisfy such property. |
| title | Regional, Lattice and Logical Representations of Neural Networks |
| topic | Logic in Computer Science Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2506.05834 |