Frontiers

A new approach for modeling generalization gradients: a case for hierarchical models

A case is made for the use of hierarchical models in the analysis of generalization gradients. Hierarchical models overcome several restrictions that are imposed by repeated measures ...
IEEE

Formal limitations of sample-wise information-theoretic generalization bounds

Abstract: Some of the tightest information-theoretic generalization bounds depend on the average information between the learned hypothesis and a single training example. However, these sample-wise ...
Frontiers

Successful generalization of conceptual knowledge after training to remember specific events

Introduction: Categorization involves grouping information to make inferences and support novel decisions. In the laboratory, category learning tasks commonly involve ...
GitHub

Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies

An agent with mid-level perception navigating inside a building. Summary: How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform ...
Microsoft

Slow down to avoid a hasty generalization fallacy

Picture this: You attend a concert to see a band perform for the first time and notice that the audience is mostly female. Based on this observation, you draw the conclusion that only women listen to ...
GitHub

FSG: Fuzzy Stacked Generalization

example_fsg.m: An example for data classification using Fuzzy Stacked Generalization (FSG). fsg.m: An implementation of Fuzzy Stacked Generalization. fknn.m: An implementation of Fuzzy k-NN classifier ...