Recent work on unsupervised feature learning has shown that learning on polynomial expansions of input patches, such as on pair-wise products of pixel intensities, can improve the...
—We consider a general wireless channel model for different types of code-division multiple access (CDMA) and space-division multiple-access (SDMA) systems with isometric random ...
As nonnegative tensor factorization (NTF) is particularly useful for the problem of underdetermined linear transform model, we performed NTF on the EEG data recorded from 14 electr...
Fengyu Cong, Anh Huy Phan, Piia Astikainen, Qibin ...
The effort and time required to develop user interface models has been one of the main limitations to the adoption of model-based approaches, which enable intelligent processing o...
Federico Bellucci, Giuseppe Ghiani, Fabio Patern&o...
Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for...
Jasper Snoek, Ryan Prescott Adams, Hugo Larochelle