We present algorithms for automatic feature selection for unsupervised structure discovery from video sequences. Feature selection in this scenario is hard because of the absence ...
It is well known that frame independence assumption is a fundamental limitation of current HMM based speech recognition systems. By treating each speech frame independently, HMMs ...
Abstract. Gaussian processes have successfully been used to learn preferences among entities as they provide nonparametric Bayesian approaches for model selection and probabilistic...
This paper introduces the sparse multilayer perceptron (SMLP) which learns the transformation from the inputs to the targets as in multilayer perceptron (MLP) while the outputs of...