Abstract. The underdetermined blind audio source separation problem is often addressed in the time-frequency domain by assuming that each time-frequency point is an independently d...
Abstract. This paper proposes a novel algorithm based on informax for postnonlinear blind source separation. The demixing system culminates to a neural network with sandwiched stru...
Chunhou Zheng, Deshuang Huang, Zhan-Li Sun, Li Sha...
One of the applications of wireless sensor networks currently undergoing active research focuses on the scenario where the information generated by a data source S is simultaneousl...
Javier Del Ser, Javier Garcia-Frias, Pedro M. Cres...
We show that, given data from a mixture of k well-separated spherical Gaussians in Rd, a simple two-round variant of EM will, with high probability, learn the parameters of the Ga...
We transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model th...