Sciweavers

Share
ICML
2010
IEEE

Hilbert Space Embeddings of Hidden Markov Models

9 years 1 months ago
Hilbert Space Embeddings of Hidden Markov Models
Hidden Markov Models (HMMs) are important tools for modeling sequence data. However, they are restricted to discrete latent states, and are largely restricted to Gaussian and discrete observations. And, learning algorithms for HMMs have predominantly relied on local search heuristics, with the exception of spectral methods such as those described below. We propose a nonparametric HMM that extends traditional HMMs to structured and non-Gaussian continuous distributions. Furthermore, we derive a localminimum-free kernel spectral algorithm for learning these HMMs. We apply our method to robot vision data, slot car inertial sensor data and audio event classification data, and show that in these applications, embedded HMMs exceed the previous state-of-the-art performance.
Le Song, Sajid M. Siddiqi, Geoffrey J. Gordon, Ale
Added 09 Nov 2010
Updated 09 Nov 2010
Type Conference
Year 2010
Where ICML
Authors Le Song, Sajid M. Siddiqi, Geoffrey J. Gordon, Alexander J. Smola
Comments (0)
books