Alert button
Picture for Ronny Luss

Ronny Luss

Alert button

Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI

Jun 22, 2022
Q. Vera Liao, Yunfeng Zhang, Ronny Luss, Finale Doshi-Velez, Amit Dhurandhar

Figure 1 for Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI
Figure 2 for Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI
Figure 3 for Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI
Figure 4 for Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI
Viaarxiv icon

Local Explanations for Reinforcement Learning

Feb 08, 2022
Ronny Luss, Amit Dhurandhar, Miao Liu

Figure 1 for Local Explanations for Reinforcement Learning
Figure 2 for Local Explanations for Reinforcement Learning
Figure 3 for Local Explanations for Reinforcement Learning
Figure 4 for Local Explanations for Reinforcement Learning
Viaarxiv icon

Auto-Transfer: Learning to Route Transferrable Representations

Feb 04, 2022
Keerthiram Murugesan, Vijay Sadashivaiah, Ronny Luss, Karthikeyan Shanmugam, Pin-Yu Chen, Amit Dhurandhar

Figure 1 for Auto-Transfer: Learning to Route Transferrable Representations
Figure 2 for Auto-Transfer: Learning to Route Transferrable Representations
Figure 3 for Auto-Transfer: Learning to Route Transferrable Representations
Figure 4 for Auto-Transfer: Learning to Route Transferrable Representations
Viaarxiv icon

AI Explainability 360: Impact and Design

Sep 24, 2021
Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilovic, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang

Figure 1 for AI Explainability 360: Impact and Design
Figure 2 for AI Explainability 360: Impact and Design
Figure 3 for AI Explainability 360: Impact and Design
Figure 4 for AI Explainability 360: Impact and Design
Viaarxiv icon

Let the CAT out of the bag: Contrastive Attributed explanations for Text

Sep 16, 2021
Saneem Chemmengath, Amar Prakash Azad, Ronny Luss, Amit Dhurandhar

Figure 1 for Let the CAT out of the bag: Contrastive Attributed explanations for Text
Figure 2 for Let the CAT out of the bag: Contrastive Attributed explanations for Text
Figure 3 for Let the CAT out of the bag: Contrastive Attributed explanations for Text
Figure 4 for Let the CAT out of the bag: Contrastive Attributed explanations for Text
Viaarxiv icon

Towards Better Model Understanding with Path-Sufficient Explanations

Sep 13, 2021
Ronny Luss, Amit Dhurandhar

Figure 1 for Towards Better Model Understanding with Path-Sufficient Explanations
Figure 2 for Towards Better Model Understanding with Path-Sufficient Explanations
Figure 3 for Towards Better Model Understanding with Path-Sufficient Explanations
Figure 4 for Towards Better Model Understanding with Path-Sufficient Explanations
Viaarxiv icon

One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques

Sep 14, 2019
Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilović, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang

Figure 1 for One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
Figure 2 for One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
Figure 3 for One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
Figure 4 for One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
Viaarxiv icon

Leveraging Simple Model Predictions for Enhancing its Performance

May 30, 2019
Amit Dhurandhar, Karthikeyan Shanmugam, Ronny Luss

Figure 1 for Leveraging Simple Model Predictions for Enhancing its Performance
Figure 2 for Leveraging Simple Model Predictions for Enhancing its Performance
Figure 3 for Leveraging Simple Model Predictions for Enhancing its Performance
Figure 4 for Leveraging Simple Model Predictions for Enhancing its Performance
Viaarxiv icon

Generating Contrastive Explanations with Monotonic Attribute Functions

May 29, 2019
Ronny Luss, Pin-Yu Chen, Amit Dhurandhar, Prasanna Sattigeri, Karthikeyan Shanmugam, Chun-Chen Tu

Figure 1 for Generating Contrastive Explanations with Monotonic Attribute Functions
Figure 2 for Generating Contrastive Explanations with Monotonic Attribute Functions
Figure 3 for Generating Contrastive Explanations with Monotonic Attribute Functions
Figure 4 for Generating Contrastive Explanations with Monotonic Attribute Functions
Viaarxiv icon