research
∙
01/21/2019
Calibration with Bias-Corrected Temperature Scaling Improves Domain Adaptation Under Label Shift in Modern Neural Networks
Label shift refers to the phenomenon where the marginal probability p(y)...
share
research
∙
10/31/2018
TF-MoDISco v0.4.4.2-alpha: Technical Note
TF-MoDISco (Transcription Factor Motif Discovery from Importance Scores)...
research
∙
07/26/2018
Computationally Efficient Measures of Internal Neuron Importance
The challenge of assigning importance to individual neurons in a network...
research
∙
02/20/2018
Learning to Abstain via Curve Optimization
In practical applications of machine learning, it is often desirable to ...
research
∙
04/10/2017
Learning Important Features Through Propagating Activation Differences
The purported "black box"' nature of neural networks is a barrier to ado...
research
∙
05/05/2016