Building Transparent Models
Transparency has become a key desideratum of machine learning. Properties such as interpretability or robustness are indispensable when model predictions are fed into mission critical applications or those dealing with sensitive/controversial topics (e.g., social, legal, financial, medical, or secur...
Main Author: | Lee, Guang-He |
---|---|
Other Authors: | Jaakkola, Tommi S. |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2022
|
Online Access: | https://hdl.handle.net/1721.1/139573 https://orcid.org/0000-0001-6561-0692 |
Similar Items
-
Review of Transparent and Semi-Transparent Building-Integrated Photovoltaics for Fenestration Application Modeling in Building Simulations
by: Joaquim Romaní, et al.
Published: (2022-04-01) -
Building envelope: techniques, languages, transparencies
by: Alessandro Claudi de Saint Mihiel
Published: (2022-07-01) -
Improving the quality and transparency of building life cycle assessment
by: Hsu, Sophia Lisbeth
Published: (2012) -
The Challenge for Building Integration of Highly Transparent Photovoltaics and Photoelectrochromic Devices
by: Alessandro Cannavale, et al.
Published: (2020-04-01) -
Building Secure and Transparent Elections Through Standard Operating Procedures
by: Alvarez, R. Michael, et al.
Published: (2015)