Hewlett-Packard Development Company, L.p.

Entit Software LLC

Stephane Chiocchetti

George H Forman

Evan Randy Kirshenbaum

Kave Eshghi

Henri Jacques Suermondt

A method and system of providing training information for training a categorizer includes receiving a query relating to at least one category and identifying at least one case within a data set that matches the query. The method and system receives one of a first indication that the identified at least one case belongs to the category, and a second indication that the identified at least one case does not belong to the category. Training information is modified based on receiving one of the first indication and second indication.

Providing training information for training a categorizer

A method, apparatus, and system identity files with similar content. One embodiment is a method that divides files into plural segments. The method computes a hash value and a size for each of the plural segments of the files. In order to identify which files have similar content, the method adds together segments common between files. File similarity information of files with similar content is output.

Identification of files with similar content

An apparatus and methods for feature selection are disclosed. The feature selection apparatus and methods allow for determining a set of final features corresponding to features common to features within a set of frequent features of target dataset and a plurality of features within a training dataset. The feature selection apparatus and methods also allow for removing features within a target dataset and a training dataset that are not within a set of most predictive features.

Method and medium for feature selection of partially labeled data

An apparatus and methods for feature selection and classifier builder are disclosed. The feature selection apparatus allows for removal of bias features. The classifier builder apparatus allows building a classifier using non-biased features. The feature selection methods disclosed teach how to remove bias features. The classifier builder methods disclosed teach how to build a classifier with non-biased features.

Preparing data for machine learning

A first set of classifiers are trained to predict categories using attributes of cases. A second set of a classifiers are also trained to predict the categories using the attributes of the cases. In addition, the second set of classifiers use the predictions from at least one of the classifiers in the first set to make predictions.

Growing community of inventors

Antony, France

Stephane Chiocchetti