Zhang, R., P. Madumal, T. Miller, K. A. Ehinger, and B. I. P. Rubinstein. “Invertible Concept-Based Explanations for CNN Models With Non-Negative Concept Activation Vectors”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 13, May 2021, pp. 11682-90, doi:10.1609/aaai.v35i13.17389.