From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks
Neurosymbolic Artificial Intelligence,
doi: 10.48550/arXiv.2310.11884
- Jul 2024

There is no abstract

@Article{LLW24, author = {Lee, Jae Hee and Lanza, Sergio and Wermter, Stefan}, title = {From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks}, booktitle = {}, journal = {Neurosymbolic Artificial Intelligence}, editors = {}, number = {}, volume = {}, pages = {}, year = {2024}, month = {Jul}, publisher = {}, doi = {10.48550/arXiv.2310.11884}, }