Combining evolution strategy and gradient descent method for discriminative learning of bayesian classifiers


The optimization method is one of key issues in discriminative learning of pattern classifiers. This paper proposes a hybrid approach of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) and the gradient decent method for optimizing Bayesian classifiers under the SOFT target based Max-Min posterior Pseudo-probabilities (Soft-MMP) learning… (More)
DOI: 10.1145/1569901.1569972

5 Figures and Tables


  • Presentations referencing similar topics