1. Exemplary natural images explain cnn ac-tivations better than state-of-the-art feature visualization;borowski;ar Xiv preprint,2020
2. How can i explain this to you? an empirical study of deep neural net-work explanation methods;jeyakumar;Advances in neural information processing systems,2020
3. Self-consistent trajectory autoencoder: Hierarchical rein-forcement learning with trajectory embeddings;co-reyes;International con-ference on machine learning,2018
4. Inforl: Interpretable re-inforcement learning using information maximization;hayat;ArXiv Preprint,2019
5. The bayesian case model: A generative approach for case-based reasoning and prototype classification;kim;Advances in neural information processing systems,2014