• Publications
  • Influence
Making Rational Decisions Using Adaptive Utility Elicitation
TLDR
We propose an algorithm that interleaves the analysis of the decision problem and utility elicitation to allow these two tasks to inform each other. Expand
Defining Explanation in Probabilistic Systems
TLDR
We examine two representative approaches to explanation in the literature-- Gardenfors and Pearl--and show that both suffer from significant problems. Expand
Utilities as Random Variables: Density Estimation and Structure Discovery
TLDR
We argue that the a person's utility value can be treated as we treat other domain attributes: as a random variable with a density function over its possible values. Expand
Case Report: Identifying Smokers with a Medical Extraction System
TLDR
The Clinical Language Understanding group at Nuance Communications has developed a medical information extraction system that combines a rule-based extraction engine with machine learning algorithms to identify and categorize references to patient smoking in clinical reports. Expand
Aggregating Learned Probabilistic Beliefs
TLDR
We propose a LinOP-based learning algorithm, inspired by the techniques developed for Bayesian learning, which aggregates the experts' distributions represented as Bayesian networks. Expand
Explaining Predictions in Bayesian Networks and Influence Diagrams
TLDR
We analyze the issues involved in defining, computing and evaluating such explanations and present an algorithm to compute them. Expand
Utility Elicitation as a Classification Problem
TLDR
We investigate the application of classification techniques to utility elicitation. Expand
Axiomatic Interpretability for Multiclass Additive Models
TLDR
We generalize a state-of-the-art GAM learning algorithm based on boosted trees to the multiclass setting, showing that this multiclass algorithm outperforms existing GAM learning algorithms and sometimes matches the performance of full complexity models such as gradient boosted trees. Expand
Utility Elicitation as a Classiication Problem
The majority of real-world probabilistic systems are used by more than one user, thus a utility model must be elicited separately for each new user. Utility elicitation is long and tedious ,Expand
...
1
2
...