Competitive training in hidden Markov models

The use of hidden Markov models is placed in a connectionist framework, and an alternative approach to improving their ability to discriminate between classes is described. Using a network style of training, a measure of discrimination based on the a posteriori probability of state occupation is proposed, and the theory for its optimization using error back-propagation and gradient ascent is presented. The method is shown to be numerically well behaved, and results are presented which demonstrate that when using a simple threshold test on the probability of state occupation, the proposed optimization scheme leads to improved recognition performance.

Plenary talk - Applied HTS research and practical applications in Europe

The development of long-length, high current density Bi2Sr 2CaCu2Ox wires and (RE)Ba2Cu 3Oy coated conductors has now advanced such that superconducting magnets for energy applications and high field applications are progressing rapidly. Europe, along with China, Korea the US and Japan is an important player in the development and exploitation of High Temperature Superconductors in practical applications. © 2013 IEEE.