CORR
2016
Springer
10 years 1 months ago
2016
Springer
In Twitter, and other microblogging services, the generation of new content by the crowd is often biased towards immediacy: what is happening now. Prompted by the propagation of c...
CORR
2016
Springer
10 years 1 months ago
2016
Springer
104
click to vote
CORR
2016
Springer
10 years 1 months ago
2016
Springer
We provide the first experimental results on non-synthetic datasets for the quasidiagonal Riemannian gradient descents for neural networks introduced in [Oll15]. These include th...
92
Voted
CORR
2016
Springer
10 years 1 months ago
2016
Springer
Abstract. We give an algorithm for computing approximate PSD factorizations of nonnegative matrices. The running time of the algorithm is polynomial in the dimensions of the input ...
139
Voted
CORR
2016
Springer
10 years 1 months ago
2016
Springer
Abstract—We demonstrate a new deep learning autoencoder network, trained by a nonnegativity constraint algorithm (NCAE), that learns features which show part-based representation...