Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying data objects. One of the methods includes obtaining data that associates each term in a vocabulary of terms with a respective high-dimensional representation of the term; obtaining classification data for a data object, wherein the classification data includes a respective score for each of a plurality of categories, and wherein each of the categories is associated with a respective category label; computing an aggregate high-dimensional representation for the data object from high-dimensional representations for the category labels associated with the categories and the respective scores; identifying a first term in the vocabulary of terms having a high-dimensional representation that is closest to the aggregate high-dimensional representation; and selecting the first term as a category label for the data object.

Abstract: Systems and techniques are disclosed for labeling objects within an image. The objects may be labeled by selecting an option from a plurality of options such that each option is a potential label for the object. An option may have an option score associated with. Additionally, a relation score may be calculated for a first option and a second option corresponding to a second object in an image. The relation score may be based on a frequency, probability, or observance corresponding to the co-occurrence of text associated with the first option and the second option in a text corpus such as the World Wide Web. An option may be selected as a label for an object based on a global score calculated based at least on an option score and relation score associated with the option.

Abstract: Methods, systems and apparatus for identifying result images for a query image. One or more labels that are associated with the query image are obtained. Candidate images matching the query labels are identified. Visual similarity scores are generated for the candidate images. Each visual similarity score represents the visual similarity of a respective candidate image to the query image. Relevance scores are generated for each of the candidate images based on the visual similarity scores. Each relevance score represents a measure of relevance of the respective candidate images to the query image. The candidate images are ranked based on the relevance scores, a highest ranking subset of the candidate images being identified as result images and referenced by image search results. The result images can be candidate images that satisfy a similarity condition relative to the query image and other result images.

Abstract: Self-terminating prediction trees are a generalization of decision trees in which each node is associated with a real-valued prediction. Instead of having a separate pruning phase, a self-terminating tree may be constructed by applying various limits during tree growth that prevent nodes that add little or no additional decision power from being grown within the tree. The prediction tree is learned by performing a penalized empirical risk minimization task, based upon the use of prediction values and functional tree complexity. A separate pruning phase is not required, since the tree self-terminates further growth.

Abstract: Methods, systems and apparatus for identifying result images for a query image. One or more labels that are associated with the query image are obtained. Candidate images matching the query labels are identified. Visual similarity scores are generated for the candidate images. Each visual similarity score represents the visual similarity of a respective candidate image to the query image. Relevance scores are generated for each of the candidate images based on the visual similarity scores. Each relevance score represents a measure of relevance of the respective candidate images to the query image. The candidate images are ranked based on the relevance scores, a highest ranking subset of the candidate images being identified as result images and referenced by image search results. The result images can be candidate images that satisfy a similarity condition relative to the query image and other result images.

Abstract: Systems and methods to deliver malformed data for software application fuzzing are described. In one aspect, a fuzzing engine receives well-formed valid input data from a test automation tool. The received data is for input into a software application to implement a functional test. Responsive to receiving the well-formed valid input data, the fuzzing engine automatically generates corresponding malformed data based on characteristics of the well-formed valid input data. The application is then automatically fuzzed with the malformed data to notify an end-user of any security vulnerabilities in one or more code paths of the application used to process the malformed data.

Abstract: Systems and methods to deliver malformed data for software application fuzzing are described. In one aspect, a fuzzing engine receives well-formed valid input data from a test automation tool. The received data is for input into a software application to implement a functional test. Responsive to receiving the well-formed valid input data, the fuzzing engine automatically generates corresponding malformed data based on characteristics of the well-formed valid input data. The application is then automatically fuzzed with the malformed data to notify an end-user of any security vulnerabilities in one or more code paths of the application used to process the malformed data.

Abstract: A system for understanding entries, such as speech, develops a classifier by employing prior knowledge with which a given corpus of training entries is enlarged threefold. A rule is created for each of the labels employed in the classifier, and the created rules are applied to the given corpus to create a corpus of attachments by appending a weight of ?p(x), or 1??p(x), to labels of entries that meet, or fail to meet, respectively, conditions of the labels' rules, and to also create a corpus of non-attachments by appending a weight of 1??p(x), or ?p(x), to labels of entries that meet, or fail to meet conditions of the labels' rules.

Abstract: A system for understanding entries, such as speech, develops a classifier by employing prior knowledge with which a given corpus of training entries is enlarged threefold. A rule is created for each of the labels employed in the classifyier, and the created rules are applied to the given corpus to create a corpus of attachments by appending a weight of ?p(x), or 1??p(x), to labels of entries that meet, or fail to meet, respectively, conditions of the labels' rules, and to also create a corpus of non-attachments by appending a weight of 1??p(x), or ?p(x), to labels of entries that meet, or fail to meet conditions of the labels' rules.

Abstract: A system for understanding entries, such as speech, develops a classifier by employing prior knowledge with which a given corpus of training entries is enlarged threefold. The prior knowledge is embodied in a rule, combined from separate rules created for each label outputted by the classifier, each of which includes a weight measure p(x). A first a set of created entries for increasing the corpus of training entries is created by attaching all labels to each entry of the original corpus of training entries, with a weight &eegr;p(x), or &eegr;(1−p(x)), in association with each label that meets, or fails to meet, the condition specified for the label, &eegr; being a preselected positive number. The second set of is created by not attaching any of the labels to each of the original corpus of training entries, with a weight of &eegr;(1−p(x)), or &eegr;p(x), in association with each label that meets, or fails to meet, the condition specified for the label.

Abstract: A method and apparatus are provided for multi-class, mutli-label information categorization. A weight is assigned to each information sample in a training set, the training set containing a plurality of information samples, such as text documents, and associated labels. A base hypothesis is determined to predict which labels are associated with a given information sample. The base hypothesis predicts whether or not each label is associated with information sample or predicts the likelihood that each label is associated with the information sample. In the case of a document, the base hypothesis evaluates words in each document to determine one or more words that predict the associated labels. When a base hypothesis is determined, the weight assigned to each information sample in the training set is modified based on the base hypothesis predictions.

Abstract: An information retrieval system finds information in a Distributed Information System (DIS), e.g. the Internet using query learning and meta search for adding documents to resource directories contained in the DIS. A selection means generates training data characterized as positive and negative examples of a particular class of data residing in the DIS. A learning means generates from the training data at least one query that can be submitted to any one of a plurality of search engines for searching the DIS to find “new” items of the particular class. An evaluation means determines and verifies that the new item(s) is a new subset of the particular class and adds or updates the particular class in the resource directory.

Abstract: Myoelectric and wireless technologies are used for the control of a portable electronic device, such as a cellular telephone or a personal digital assistant (PDA). That is, a portable electronic device has a wireless myoelectric user interface. An apparatus includes a material which forms a forearm or wrist band, myoelectric sensors attached to the band, a digital processor coupled to the myoelectric sensors, and a wireless transmitter coupled to the digital processor. The apparatus is operative to sense and detect particular hand and/or finger gestures, and to broadcast control signals corresponding to the gestures for operative control of the portable electronic device.

Abstract: Myoelectric and wireless technologies are used for the control of a portable electronic device, such as a cellular telephone or a personal digital assistant (PDA). That is, a portable electronic device has a wireless myoelectric user interface. An apparatus includes a material which forms a forearm or wrist band, myoelectric sensors attached to the band, a digital processor coupled to the myoelectric sensors, and a wireless transmitter coupled to the digital processor. The apparatus is operative to sense and detect particular hand and/or finger gestures, and to broadcast control signals corresponding to the gestures for operative control of the portable electronic device.