Search Results for author:
Found 3 papers, 1 papers with code
Measuring and Mitigating Local Instability in Deep Neural Networks
We formulate the model stability problem by studying how the predictions of a model change, even when it is retrained on the same data, as a consequence of stochasticity in the training process.
Fair-Net: A Network Architecture For Reducing Performance Disparity Between Identifiable Sub-Populations
This problem is aggravated across many domains where datasets are class imbalanced, with a minority class far rarer than the majority class.
Deep learning long-range information in undirected graphs with wave networks
Some of these algorithms depend on propagating information between distant nodes in a graph.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
