Sentence examples for binary classifier trained on from inspiring English sources

However, we point out that this is not necessarily the case: As described in the Multi-label multi-class naïve Bayes section, our MMM is not a mere combination of |L| single-label binary classifiers, each being a one-vs-all binary classifier trained on a single-label dataset that ignores possible overlaps among the target proteins at the outset.

Consider a binary classifier trained on a binary target [ l| m] ∈ B where indices l, m ∈ 2 C - { C, φ} denote two disjoint (l ∩ m = φ) subsets of class labels and B is a certain set of targets.

The steganographic security is evaluated empirically using binary classifiers trained on a given cover source and its stego version embedded with a fixed payload.

Using binary classifiers trained on nucleosome landscapes at the gene boundaries from two independent nucleosome positioning data sets, we were able to detect a total of 231 regions containing putative genes in the genome of Plasmodium falciparum, of which 67 highly confident genes were found in both data sets.

Although we only focus here on binary classification, the techniques can be easily extended to problems involving more than two classes using, for example, a series of binary classifiers trained to discriminate each class against all others.

Our first classifier is a standard logistic regression classifier trained on tweets.

The classifier trained on the training set was tested in a new group of 72 tumours.

Lastly, can predictive classifiers trained on one platform perform well on data generated using another platform?

A Random Forest binary classifier [42] trained on interaction energy components and 20 residue type counts was used to predict whether or not each 9-mer fragment bound to the MHC allotype of interest.

To differentiate gene start sites and intergenic regions, a binary classifier was trained on positive class windows and negative class windows.

Referring to the number of classifiers trained on each training set from above, we trained in total between 133·10·300 and 185·10·300 different classifiers during evaluation of individual endpoints.