Interpretable Differencing of Machine Learning Models
- Swagatam Haldar
- Diptikalyan Saha
- et al.
- 2023
- UAI 2023
Bio
Rahul Nair is Senior Research Scientist at IBM Research based in Dublin, Ireland. His current research interests are in trusted AI, model transparency, explainability, and technology for development. His expertise is in optimization, machine learning which he has applied across sectors particularly transportation, healthcare, and business computing. He holds a Ph.D. from University of Maryland College Park.
Publications
Co-creating a globally interpretable model with human inputs
- 2023
- ICML 2023
An Explainable Forecasting System for Humanitarian Needs Assessment
- Rahul Nair
- Bo Schwartz Madsen
- et al.
- 2023
- IAAI 2023
On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach
- Dennis Wei
- Rahul Nair
- et al.
- 2022
- NeurIPS 2022
Assessing Users' Ability To Modify And Communicate Ai Models' Decision Boundaries Via A Low-code, Rules-based Approach
- 2022
- INFORMS 2022
FROTE: Feedback Rule-Driven Oversampling for Editing Models
- Oznur Alkan
- Dennis Wei
- et al.
- 2022
- MLSys 2022
Boolean Decision Rules for Reinforcement Learning Policy Summarisation
- James McCarthy
- Rahul Nair
- et al.
- 2022
- IJCAI 2022
Contrastive Explanations for Comparing Preferences of Reinforcement Learning
- Jasmina Gajcin
- Rahul Nair
- et al.
- 2022
- AAAI 2022
Prospective Explanations: An Interactive Mechanism for Model Understanding
- Rahul Nair
- Pierpaolo Tommasi
- 2021
- NeurIPS 2021
AIMEE: Interactive model maintenance with rule-based surrogates
- Owen Cornec
- Rahul Nair
- et al.
- 2021
- NeurIPS 2021
Patents
- 18 Sep 2023
- US
- 11763320
- 08 May 2023
- US
- 11645595
- 23 Jan 2023
- US
- 11562087
- 16 Jan 2023
- US
- 11556938
- 21 Nov 2022
- US
- 11507890
- 08 Aug 2022
- US
- 11410184
- 25 Jul 2022
- US
- 11397954
- 11 Jul 2022
- US
- 11386265
- 14 Mar 2022
- US
- 11276176
- 14 Mar 2022
- US
- 11276011
Projects
AIMEE
AI model explorer and editor tool.
Fluorescence-based Digital Surgery Decision Support
Analyzing and visualizing differences in blood flow patterns, made visible with fluorescent dyes and multispectral imaging.
AutoFair: Human-compatible Automation of Fairness in AI
Addressing the need for trusted AI in a range of practical industrial applications from recruitment, to fintech and advertising.
Top collaborators
ED
Elizabeth Daly
STSM, Research Manager, Interactive AI Group
DW
Dennis Wei
Senior Research Scientist
OC
RM
Radu Marinescu
Research Staff Member