Search Results for author:
Found 4 papers, 2 papers with code
Robust Neural Regression via Uncertainty Learning
Deep neural networks tend to underestimate uncertainty and produce overly confident predictions.
On the Inter-relationships among Drift rate, Forgetting rate, Bias/variance profile and Error
These hypotheses lead to the concept of the sweet path, a path through the 3-d space of alternative drift rates, forgetting rates and bias/variance profiles on which generalization error will be minimized, such that slow drift is coupled with low forgetting and low bias, while rapid drift is coupled with fast forgetting and low variance.
On the Effectiveness of Discretizing Quantitative Attributes in Linear Classifiers
It is often motivated by the limitation of some learners to qualitative data.
Deep Broad Learning - Big Models for Big Data
For some learning tasks there is power in learning models that are not only Deep but also Broad.
