Up-propagation is an algorithm for inverting and learning neural network generative models. Sensory input is processed by inverting a model that generates patterns from hidden var...
In lamprey, the supraspinal control of velocity is mainly accomplished by the reticulospinal (RS) system. During locomotion, RS neurones are rhythmically active with a cycle durat...
This paper presents a new method that uses orthogonalized features for time series clustering and classification. To cluster or classify time series data, either original data or...
In this study, a system that discriminates laughter from speech by modelling the relationship between audio and visual features is presented. The underlying assumption is that thi...
Abstract—Inspired by the recent development of optical queueing theory, in this paper we study a class of multistage interconnection networks (MINs), called twister networks. Unl...
Ching-Ming Lien, Cheng-Shang Chang, Jay Cheng, Dua...