An Algorithm of Score Function Generation using Convolution-FFT in Independent Component Analysis

Independent component analysis with the EM and FFT algorithm.

​Rank based Least-squares Independent Component Analysis

  In this paper, we propose a nonparametric rank-based alternative to the least-squares independent component analysis algorithm developed. The basic idea is to estimate the squared-loss mutual information, which used as the objective function of the algorithm, based on its copula density version. Therefore, no marginal densities have to be estimated. We provide empirical evaluation of th...

Pruning of Winograd and FFT Based Convolution Algorithm

Winogradand FFT-based convolution are two efficient convolution algorithms targeting high-performance inference. Their efficiency comes from the reduction of the number of multiplication operations due to linear and Fourier transforms. However, the two existing approaches cannot handle efficient compression of the neural network, which might contribute significant improvement in computation and...

Noisy image processing using the independent component analysis algorithm AMUSE

In this article we investigate the performance of the ICA algorithm AMUSE when applied to images contaminated by noise. The classes of noise we are using have gaussian, multiplicative and impulsive distributions. We find that AMUSE copes surprisingly well with the different types of noise, including multiplicative noise.

‏‎interpersonal function of language in subtitling

‏‎translation as a comunicative process is always said to be associated with various aspects of meaning loss or gain. subtitling as a mode of translating, due to special discoursal and textual conditions imposed upon it, is believed to be an obvious case of this loss or gain. presenting the spoken sound track of a film in writing and synchronizing the perception of this text by the viewers with...