James Wexler

Interpretability Beyond Feature Attribution: Quantitative Testing with\n Concept Activation Vectors (TCAV)

Been Kim, Martin Wattenberg, Justin Gilmer et al. · arXiv (Cornell University) · 2017 · 732 citations · Full text

The What-If Tool: Interactive Probing of Machine Learning Models

James Wexler, Mahima Pushkarna, Tolga Bolukbasi et al. · IEEE Transactions on Visualization and Computer Graphics · 2019 · 492 citations · Full text

Artificial Intelligence, Engineering, Machine Learning +19

Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)

Been Kim, Martin Wattenberg, Justin Gilmer et al. · arXiv (Cornell University) · 2017 · 476 citations · Full text

Concept Formation, Convolutional Neural Network, Engineering +27

Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow

Kanit Wongsuphasawat, Daniel Smilkov, James Wexler et al. · IEEE Transactions on Visualization and Computer Graphics · 2017 · 326 citations

Dataflow Graphs, Interactive Visualization, Graph Neural Network +12

The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models

Ian Tenney, James Wexler, Jasmijn Bastings et al. · 2020 · 128 citations · Full text

Engineering, Semantics, System Demonstrations +25