Concepedia

Neural Network Interpretability

Neural Network Interpretability is a methodological framework within deep learning that enables the elucidation and systematic understanding of the decision-making processes of neural networks by identifying the structural and functional contributions of their internal components.

724

Publications

62.5K

Citations

2.4K

Authors

803

Institutions

Publications per year

2017–2026

683

Variants

Interpretability Of Neural Networks

Parents

Publications

724

Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks

Aditya Chattopadhay, Anirban Sarkar, Prantik Howlader et al. · 2018 · 3.1K citations · Full text

, , +15

Methods for interpreting and understanding deep neural networks

Grégoire Montavon, Wojciech Samek, Klaus‐Robert Müller · Digital Signal Processing · 2017 · 2.7K citations · Full text

, , +14

Learning Important Features Through Propagating Activation Differences

Avanti Shrikumar, Peyton Greenside, Anshul Kundaje · arXiv (Cornell University) · 2017 · 2.4K citations · Full text

, , +14

TabNet: Attentive Interpretable Tabular Learning

Sercan Ö. Arık, Tomas Pfister · 2021 · 1.5K citations · Full text

, , +16

Explaining nonlinear classification decisions with deep Taylor decomposition

Grégoire Montavon, Sebastian Lapuschkin, Alexander Binder et al. · Pattern Recognition · 2016 · 1.4K citations · Full text

, , +15

1–5 of 724

Authors

2.4K

  1. KM
    Klaus‐Robert Müller

    Technische Universität Berlin, Germany

    16 publications · 6.3K citations

    16

    h-index

  2. BK
    Been Kim

    Google (United States), United States

    15 publications · 2.7K citations

    14

    h-index

  3. WS
    Wojciech Samek

    Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, Germany

    13 publications · 6.1K citations

    13

    h-index

  4. AS
    Agus Sudjianto

    Ford Motor Company (United States), United States

    8 publications · 417 citations

    8

    h-index

  5. QZ
    Quanshi Zhang

    Shanghai Jiao Tong University, China

    8 publications · 2K citations

    8

    h-index

1–5 of 2.4K

Institutions

803

  1. Google (United States)

    Mountain View, United States

    17 h-index

    47 publications

    8.7K citations

  2. Massachusetts Institute of Technology

    Cambridge, United States

    15 h-index

    35 publications

    3.9K citations

  3. Technische Universität Berlin

    Berlin, Germany

    13 h-index

    31 publications

    13.1K citations

  4. Tsinghua University

    Beijing, China

    13 h-index

    35 publications

    2.5K citations

  5. Stanford University

    Stanford, United States

    12 h-index

    23 publications

    9.9K citations

  6. Carnegie Mellon University

    Pittsburgh, United States

    10 h-index

    33 publications

    5.3K citations

  7. Shanghai Jiao Tong University

    Shanghai, China

    10 h-index

    34 publications

    2K citations

  8. University of Washington

    Seattle, United States

    9 h-index

    16 publications

    597 citations

1–8 of 803

Venues

  1. arXiv (Cornell University)

    Repository · 175 publications · 14.9K citations

    54

    h-index

  2. IEEE Access

    14 publications · 667 citations

    14

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 12 publications · 1.1K citations

    12

    h-index

  4. 7

    h-index

  5. Knowledge-Based Systems

    7 publications · 267 citations

    7

    h-index

1–5