Case-Based Decision Theory
PulseAugur coverage of Case-Based Decision Theory — every cluster mentioning Case-Based Decision Theory across labs, papers, and developer communities, ranked by signal.
-
Neural Networks Can Make Worse Decisions When Pooling Data, Study Finds
A new paper explores how neural networks can make worse decisions when combining data from different sources, a phenomenon known as preference reversal. The research identifies that refitting models on pooled data can a…
-
Neural networks risk preference reversals when trained on pooled data
A new paper explores the reliability of neural networks when trained on combined data from different sources. The research identifies that pooling data can lead to preference reversals, where a model's decisions change …
-
New theory enables exact auditing of neural network decisions
Researchers have developed a new method to audit neural network decisions by decomposing action scores into a weighted sum of training case returns. This approach, grounded in Case-Based Decision Theory (CBDT), allows f…