Sentence examples for most probable labels from inspiring English sources

Specifically, for all vector representation models (i.e., SocioDim, DeepWalk, LINE, SNBC and node2vec), we use a one-vs-rest logistic regression implemented by LibLinear [45] to return the most probable labels as described in prior work [5, 14, 17].

With widely available large-scale network data, one hot topic is how to adopt traditional classification algorithms to predict the most probable labels of nodes in a partially labeled network.

Then we identified the most probable labeling for each simulated probability vector and the one returned by FALCON using equation (1) as objective function.

To address the problem of noise and blurry boundary, segmentation methods adopted here follow conditional probability models where the most probable label of a pixel depends upon the attributes of both the pixel itself and its neighbors.

Given an item sequence, a CRF model predicts the most probable label sequence based on functions capturing characteristics of the current token and its context.

Because the graphs are small we could identify the most probable labeling by exhaustive searching.

Because the graphs are small, exhaustive search of the most probable labeling was computationally tractable.

Once the weights are learned, one can label a new sequence by finding the most probable label sequence according to P y| x).

The most probable spin label-to-spin label distances obtained for each combination of labeling sites for KCNE1 in LMPG micelles, proteoliposomes, and lipodisq nanoparticles were, in all cases, comparable (Table 1).

For each probabilistic atlas used here, deterministic parcellations were created by assigning the most probable region label to each selected voxel.

Dimension D0 is equal to the maximum of the multifractal spectrum f, when the most probable α occurs, labeled as α0.