246 citations · 640 across the 16 of their papers we have counts for
Showing 2016Show all
3 papers · 1 filter
math.OC2016
Mutual information for fitting deep nonlinear models
Jacob S. Hunter, Nathan O. Hodas
Deep nonlinear models pose a challenge for fitting parameters due to lack of knowledge of the hidden layer and the potentially non-affine relation of the initial and observed layer…
cs.LG2016★ 7 cited
Beyond Fine Tuning: A Modular Approach to Learning on Small Data
Ark Anderson, Kyle Shaffer, Artem Yankov +2
In this paper we present a technique to train neural network models on small amounts of data. Current methods for training neural networks on small amounts of rich data typically r…
cs.HC2016★ 6 cited
Adding Semantic Information into Data Models by Learning Domain Expertise from User Interaction
Nathan Oken Hodas, Alex Endert
Interactive visual analytic systems enable users to discover insights from complex data. Users can express and test hypotheses via user interaction, leveraging their domain experti…