Mind the Gap: A Generative Approach to Interpretable Feature Selection and Extraction
We present the Mind the Gap Model (MGM), an approach for interpretable feature extraction and selection. By placing interpretability criteria directly into the model, we allow for the model to both optimize parameters related to interpretability and to directly report a global set of distinguishable...
Main Authors: | Doshi-Valez, Finale, Kim, Been, Shah, Julie A |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
Format: | Article |
Language: | en_US |
Published: |
Neural Information Processing Systems Foundation Inc.
2017
|
Online Access: | http://hdl.handle.net/1721.1/109373 https://orcid.org/0000-0003-1338-8107 |
Similar Items
-
Bayesian nonparametric approaches for reinforcement learning in partially observable domains
by: Doshi-Velez, Finale
Published: (2012) -
Efficient model learning for dialog management
by: Doshi, Finale (Finale P.)
Published: (2008) -
The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification
by: Kim, Been, et al.
Published: (2014) -
Latent Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification
by: Kim, Been, et al.
Published: (2014) -
Inferring team task plans from human meetings: A generative modeling approach with logic-based prior
by: Kim, Been, et al.
Published: (2015)