On Max-Margin Markov Networks in Hierarchical Document Classification

Posted in Science on July 23, 2008


On Max-Margin Markov Networks in Hierarchical Document Classification

Lecture slides:

  • Hierarchical Multilabel Classifcation: union of partial paths model
  • Frequently used learning strategies for hierarchies
  • The classification model
  • Feature vectors
  • Loss functions for hierarchies
  • Max-margin Structured output learning
  • Optimization problem
  • Marginalized problem
  • Decomposing the model
  • Conditional Gradient method
  • Conditional Gradient Ascent
  • Using inference to find update directions
  • Experiments
  • Optimization efficiency
  • Prediction accuracy: Levelwise F1
  • Scalability?
  • Conclusions

Author: Juho Rousu, University of Helsinki

Watch Video

Tags: Science, Lectures, Computer Science, Machine Learning, VideoLectures.Net, Markov Processes