Material Detail

A Universal Kernel for Learning Regular Languages

A Universal Kernel for Learning Regular Languages

This video was recorded at 5th International Workshop on Mining and Learning with Graphs (MLG), Firenze 2007. We give a universal kernel that renders all the regular languages linearly separable. We are not able to compute this kernel efficiently and conjecture that it is intractable, but we do have an efficient ǫ-approximation

Quality

  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material

Comments

Log in to participate in the discussions or sign up if you are not already a MERLOT member.