Differences

This shows you the differences between two versions of the page.

Link to this comparison view

feature_competition [2017/03/29 20:17]
feature_competition [2017/03/29 20:17] (current)
Line 1: Line 1:
 +https://​arxiv.org/​pdf/​1703.02156v1.pdf On the Limits of Learning Representations with Label-Based Supervision
 +
 +Will the representations learned from these generative methods ever rival the quality of those from their supervised competitors?​ In this work, we argue in the affirmative,​ that from an information theoretic perspective,​ generative models have greater potential for representation learning. Based on several experimentally validated assumptions,​ we show that supervised learning is upper bounded in its capacity for representation learning in ways that certain generative models, such as Generative Adversarial Networks (GANs) are not.
 +
 +https://​arxiv.org/​abs/​1608.08984 Towards Competitive Classifiers for Unbalanced Classification Problems: A Study on the Performance Scores
 +
 +Although a great methodological effort has been invested in proposing competitive solutions to the class-imbalance problem, little effort has been made in pursuing a theoretical understanding of this matter. ​
 +
 +https://​arxiv.org/​abs/​1703.08774v1 Who Said What: Modeling Individual Labelers Improves Classification
 +
 +To make use of this extra information,​ we propose modeling the experts individually and then learning averaging weights for combining them, possibly in sample-specific ways. This allows us to give more weight to more reliable experts and take advantage of the unique strengths of individual experts at classifying certain types of data. 
 +