Due to the large number of parameters and heavy computation, real-time operation deep learning in low-performance embedded board is still difficult. Network Pruning one effective methods reduce without additional network structure modification. However, conventional method prunes redundant up same rate for all layers. It may cause a bottleneck problem, which leads performance degradation, becau...

This paper gives a detailed introduction of implementing mixture Gaussian process (MGP) model and develops its application for Bayesian optimization (BayesOpt). The also techniques MGP in finding components introduced an alternative gating network based on the Dirichlet distributions. BayesOpt using resultant significantly outperforms one regression terms efficiency test tuning hyperparameters ...

We introduce a mixture of generalized hyperbolic distributions as an alternative to the ubiquitous mixture of Gaussian distributions as well as their near relatives of which the mixture of multivariate t and skew-t distributions are predominant. The mathematical development of our mixture of generalized hyperbolic distributions model relies on its relationship with the generalized inverse Gauss...