Sentence examples for a training instance from inspiring English sources

The grey point represents a training instance, and the black points depict external instances scattered across a 2D projection of the 20 molecular feature matrix.

instance k represents the bootstrapped instance, which is the input of neural network; target k represents the desirable output if instance k is a training instance; type field has two values: "train" and "test", which labels the type of instance k.

In the case of three base classifiers, we represent the predictions of these classifiers on a training instance X as {P 1(X),P 2(X),P 3(X)}, the attribute vector for X is 〈x 1,x 2,⋯,x n 〉 if the number of attributes is n, the number of classes is m, the true class for X is expressed as l a b l e(X).

A training instance is a bag-of-words representation and is a vector of binary features.

In SGD, a training instance is selected and classified according to the current parameters of the model.

The feature set of a training instance is a combination of features from a criterion and the PICO features of the same document that same criterion belongs to.

A positive training instance was created from every event event/event time pair whose elements (1) had a temporal relation and (2) occurred in adjacent sentences, and by assigning a class value that was the relation type.

When a new training instance arrives, first the total scatter matrix is updated, then the between class scatter matrix, and finally the projection matrices are updated.

Each criterion is mapped to a single training instance.

In addition, a negative training instance was created from each pair of main events that appeared in adjacent sentences, where the main events of a sentence were simply the first and last events of a sentence.

For example, we can pool all training instances in a dictionary (hence k = n and A = D ), and then learn the non-negative coefficient vectors of a new instance, which is formulated as an one-sided model: (17) min x 1 2 b - A x 2 2 s. t. x ≥ 0. We called this model the non-negative least squares (NNLS) sparse coding.