Triadic Concept Analysis for Logic Interpretation of Simple Artificial Networks
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914244634607616 |
|---|---|
| author | Schmitt, Ingo |
| author_facet | Schmitt, Ingo |
| contents | An artificial neural network (ANN) is a numerical method used to solve complex classification problems. Due to its high classification power, the ANN method often outperforms other classification methods in terms of accuracy. However, an ANN model lacks interpretability compared to methods that use the symbolic paradigm. Our idea is to derive a symbolic representation from a simple ANN model trained on minterm values of input objects. Based on ReLU nodes, the ANN model is partitioned into cells. We convert the ANN model into a cell-based, three-dimensional bit tensor. The theory of Formal Concept Analysis applied to the tensor yields concepts that are represented as logic trees, expressing interpretable attribute interactions. Their evaluations preserve the classification power of the initial ANN model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_06229 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Triadic Concept Analysis for Logic Interpretation of Simple Artificial Networks Schmitt, Ingo Machine Learning Artificial Intelligence Logic in Computer Science I.2 An artificial neural network (ANN) is a numerical method used to solve complex classification problems. Due to its high classification power, the ANN method often outperforms other classification methods in terms of accuracy. However, an ANN model lacks interpretability compared to methods that use the symbolic paradigm. Our idea is to derive a symbolic representation from a simple ANN model trained on minterm values of input objects. Based on ReLU nodes, the ANN model is partitioned into cells. We convert the ANN model into a cell-based, three-dimensional bit tensor. The theory of Formal Concept Analysis applied to the tensor yields concepts that are represented as logic trees, expressing interpretable attribute interactions. Their evaluations preserve the classification power of the initial ANN model. |
| title | Triadic Concept Analysis for Logic Interpretation of Simple Artificial Networks |
| topic | Machine Learning Artificial Intelligence Logic in Computer Science I.2 |
| url | https://arxiv.org/abs/2601.06229 |