partial substitute
play

Partial Substitute tong-wang@uiowa.edu Poster #67 A black-box - PowerPoint PPT Presentation

Tong Wang Gaining Free or Low-Cost University of Iowa Transparency with Interpretable Tippie College of Business Partial Substitute tong-wang@uiowa.edu Poster #67 A black-box model + High predictive performance - non-interpretable An


  1. Tong Wang Gaining Free or Low-Cost University of Iowa Transparency with Interpretable Tippie College of Business Partial Substitute tong-wang@uiowa.edu

  2. Poster #67 A black-box model + High predictive performance - non-interpretable An interpretable model A hybrid of both? + interpretable - lower predictive performance

  3. Poster #67 A black-box model + High predictive performance - non-interpretable An interpretable model A hybrid of both? + interpretable - lower predictive performance A key observation: there might exist a subspace where a black-box is overkill and a simple interpretable model can perform just as well as the black-box

  4. Poster #67 A black-box model An interpretable model A hybrid of both? + High predictive performance An effective trade-off + interpretable A key observation: there might exist a subspace where a black-box is overkill and a simple interpretable model can perform just as well as the black-box The proposed solution: to substitute the black-box model with an interpretable model, where there is no or low- cost of predictive performance

  5. Poster #67 A black-box model An interpretable model A hybrid of both? + High predictive performance An effective trade-off + interpretable A key observation: there might exist a subspace where a black-box is overkill and a simple interpretable model can perform just as well as the black-box The proposed solution: to substitute the black-box model with an interpretable model, where there is no or low- cost of predictive performance Predicted by a black-box model + - Predicted by an interpretable model Predicted by an interpretable model

  6. Poster #67 A A hybrid rid pr predi dict ctive mod odel Define transparency of model: ๐ธ ๐‘— ๐ธ

  7. Poster #67 A hybrid A rid Learning Objective pr predi dict ctive โ€ข Predictive performance mod odel โ€ข Interpretability of ๐‘” ๐‘— Define transparency of model: ๐ธ ๐‘— โ€ข Transparency ๐ธ

  8. Poster #67 A hybrid A rid Learning Objective pr predi dict ctive โ€ข Predictive performance mod odel โ€ข Interpretability of ๐‘” ๐‘— Define transparency of model: ๐ธ ๐‘— โ€ข Transparency ๐ธ A Hybrid Rule Set Poster #67

  9. Poster #67 Model Training ๐‘œ { ๐‘ฆ ๐‘— } ๐‘—=1 training data ๐‘œ { (๐‘ฆ ๐‘— , ๐‘ง ๐‘— )} ๐‘—=1 Any pre-trained Training and black box Predicted labels algorithm ๐‘œ classifier { เทœ ๐‘ง ๐‘๐‘— } ๐‘—=1 Stochastic Local Search ๐‘œ { เทœ ๐‘ง ๐‘๐‘— } ๐‘—=1 Input of the based algorithm (see the training algorithm paper for more details)

  10. Poster #67 Evaluation: An efficient frontier that characterizes the trade-off between transparency and accuracy

  11. Poster #67 Performance on Juvenile dataset accuracy transparency

  12. Thank you! Poster #67 in Pacific Ballroom

Recommend


More recommend