![MAKE | Free Full-Text | Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey | HTML MAKE | Free Full-Text | Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey | HTML](https://www.mdpi.com/make/make-03-00048/article_deploy/html/images/make-03-00048-g002-550.jpg)
MAKE | Free Full-Text | Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey | HTML
![Information Bottleneck for NLP (parsing & summarization) | by Chien-Sheng (Jason) Wu | Process My Language | Medium Information Bottleneck for NLP (parsing & summarization) | by Chien-Sheng (Jason) Wu | Process My Language | Medium](https://miro.medium.com/max/1400/1*T22e-Q6IpfUsjx2b4jMkng.png)
Information Bottleneck for NLP (parsing & summarization) | by Chien-Sheng (Jason) Wu | Process My Language | Medium
![Exploring deep neural networks via layer-peeled model: Minority collapse in imbalanced training | PNAS Exploring deep neural networks via layer-peeled model: Minority collapse in imbalanced training | PNAS](https://www.pnas.org/cms/10.1073/pnas.2103091118/asset/304a4b19-8995-40dc-af0f-45077591b242/assets/images/large/pnas.202103091fig04.jpg)
Exploring deep neural networks via layer-peeled model: Minority collapse in imbalanced training | PNAS
Opening the Black Box of Deep Neural Networks via Information · Issue #37 · dais-ita/interpretability-papers · GitHub
![Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data | Nature Communications Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data | Nature Communications](https://media.springernature.com/full/springer-static/image/art%3A10.1038%2Fs41467-021-24025-8/MediaObjects/41467_2021_24025_Fig1_HTML.png)