Learn More
Deep neural networks have recently become the gold standard for acoustic modeling in speech recognition systems. The key computational unit of a deep network is a linear projection followed by a point-wise non-linearity, which is typically a logistic function. In this work, we show that we can improve generalization and make training of deep networks faster(More)
The AFLP genetic linkage maps for two poplar cultivars were constructed with the pseudo-test-cross mapping strategy. The hybrids were derived from an interspecific backcross between the female hybrid clone “TB01” (Populus tomentosa × Populus bolleana) and the male clone “LM50” (P. tomentosa). A total of 782 polymorphic fragments were obtained with a(More)
The entire genome of the A/Chicken/Hubei/C1/2007 (H9N2) virus, isolated from central China in 2007, was completely sequenced and phylogenetically analyzed. Phylogenetic analysis demonstrated that A/Chicken/Hubei/C1/2007 (H9N2) virus represents multiple reassortant lineages, with genes coming from the early mainland China strain (Ck/Bejing/1/94), an H9N2(More)
In this paper, an anatomically accurate three-dimensional finite-element (FE) model of the human lumbar spine (L2-L3) was used to study the biomechanical effects of graded bilateral and unilateral facetectomies of L3 under anterior shear. The intact L2-L3 FE model was validated under compression, tension, and shear loading and the predicted responses(More)
The QoS Steiner Tree Problem asks for the most costefficient way to multicast multimedia to a heterogeneous collection of users with different consumption rates. We assume that the cost of using a link is not constant but rather depends on the maximum bandwidth routed through the link. Formally, given a graph with costs on the edges, a source node and a set(More)