Abstract: A system and method is provided that processes a training database of human-generated requests in each of a plurality of task categories with a machine learning algorithm to develop a task classifier model that may be applied to subsequent user requests to determine the most likely one of the task categories for the subsequent user request.

Abstract: Various embodiments select features from a feature space. In one embodiment, a set of training samples and a set of test samples are received. The set of training samples includes a set of features and a class value. The set of test samples includes the set of features absent the class value. A relevancy with respect to the class value is determined for each of a plurality of unselected features based on the set of training samples. A redundancy with respect to one or more of the set of features is determined for each of the plurality of unselected features in the first set of features based on the set of training samples and the set of test samples. A set of features is selected from the plurality of unselected features based on the relevancy and the redundancy determined for each of the plurality of unselected features.

Abstract: Methods and systems for distance metric learning include generating two random projection matrices of a dataset from a d-dimensional space into an m-dimensional sub-space, where m is smaller than d. An optimization problem is solved in the m-dimensional subspace to learn a distance metric based on the random projection matrices. The distance metric is recovered in the d-dimensional space.

Abstract: A method to determine image similarities. The method may include obtaining a first image and a second image and determining a discrete transform difference between a first discrete transform of the first image and a second discrete transform of the second image. The method may also include determining multiple first intensity vectors for the first image and determining multiple second intensity vectors for the second image. The method may also include determining an intensity vector difference between the multiple first intensity vectors and the multiple second intensity vectors and determining a color difference between a first color histogram of the first image and a second color histogram of the second image. The method may also include determining a similarity between the first image and the second image based on the discrete transform difference, the intensity vector difference, and the color difference.

Abstract: Systems and methods for routing and/or servicing contacts using video analysis of one or more video streams are provided. The systems and methods are particularly applicable to a contact center.

Abstract: A method of frequency discrimination associated with the Doppler effect is presented. The method includes mapping a first signal to a first plurality of frequency bins and a second signal to a second plurality of frequency bins. The first signal and the second signal corresponding to different times. The method also includes firing a first plurality of neurons based on contents of the first plurality of frequency bins and firing a second plurality of neurons based on contents of the second plurality of frequency bins.

Abstract: Object recognition apparatus and methods useful for extracting information from sensory input. In one embodiment, the input signal is representative of an element of an image, and the extracted information is encoded in a pulsed output signal. The information is encoded in one variant as a pattern of pulse latencies relative to an occurrence of a temporal event; e.g., the appearance of a new visual frame or movement of the image. The pattern of pulses advantageously is substantially insensitive to such image parameters as size, position, and orientation, so the image identity can be readily decoded. The size, position, and rotation affect the timing of occurrence of the pattern relative to the event; hence, changing the image size or position will not change the pattern of relative pulse latencies but will shift it in time, e.g., will advance or delay its occurrence.

Abstract: Video sequence processing is described with various filtering rules applied to extract dominant features for content based video sequence identification. Active regions are determined in video frames of a video sequence. Video frames are selected in response to temporal statistical characteristics of the determined active regions. A two pass analysis is used to detect a set of initial interest points and interest regions in the selected video frames to reduce the effective area of images that are refined by complex filters that provide accurate region characterizations resistant to image distortion for identification of the video frames in the video sequence. Extracted features and descriptors are robust with respect to image scaling, aspect ratio change, rotation, camera viewpoint change, illumination and contrast change, video compression/decompression artifacts and noise.

Abstract: Disclosed herein is an Intrusion Detection System (IDS) false positive detection apparatus and method. An IDS false positive detection apparatus includes a payload extraction unit for extracting payloads by dividing each packet corresponding to an IDS detection rule into a header and a payload. A false positive payload information generation unit generates false positive payload information required to identify a false positive payload by extracting a payload of a false positive packet based on results of packet analysis received from a manager. A false positive payload determination unit transmits results of a determination of whether each payload extracted by the payload extraction unit corresponds to a false positive payload, based on the false positive payload information, to the manager.

Abstract: Methods, systems, and computer readable media for classifying application traffic at a network traffic emulation device that emulates multiple application servers are disclosed. The method may include, at a network traffic emulation device, providing a plurality of different application flows for monitoring mixed application traffic received from different client applications via a device under test on the same transport layer port. For each of the different application flows that monitor the same transport layer port, parsing a payload of received packets associated with the same session in the mixed application traffic and identifying non-matching application flows based on whether a portion of each payload matches a signature associated with the application flow.

Abstract: Systems, methods, and devices for determining whether a medical sensor has been properly applied to a patient are provided. In one embodiment, a patient monitor having such capabilities may include a medical sensor interface and data processing circuitry. The medical sensor interface may receive physiological data from a medical sensor applied to a patient. The data processing circuitry may be capable of being trained, using a learning-based algorithm, to determine whether the received physiological data indicates that the medical sensor has been properly applied to the patient.

Abstract: The present invention relates to unsupervised, supervised and reinforced learning via spiking computation. The neural network comprises a plurality of neural modules. Each neural module comprises multiple digital neurons such that each neuron in a neural module has a corresponding neuron in another neural module. An interconnection network comprising a plurality of edges interconnects the plurality of neural modules. Each edge interconnects a first neural module to a second neural module, and each edge comprises a weighted synaptic connection between every neuron in the first neural module and a corresponding neuron in the second neural module.

Abstract: A set S is initialized. Initially, S is empty; but, as the disclosed process is performed, items are added to it. It may contain one or more samples (e.g., items) from each class. One or more labeled samples for one or more classes may be obtained. A series of operations may be performed, iteratively, until a stopping criterion is reach to obtain the reduced set. For each class of the one or more classes, a point may be generated based on at least one sample in the class having a nearest neighbor in a set S with a different class label than the sample. The point may be added to the set S. The process may be repeated unless a stopping criterion is reached. A nearest neighbor for a submitted point in the set S may be identified and a candidate nearest neighbor may be output for the submitted point.

Abstract: Systems and methods are disclosed herein to provide communication test systems for the testing of packet data communication devices, systems and networks. According to one aspect of the subject matter described herein, a test system containing an integrated traffic, protocol and waveform analyzer is disclosed that includes a traffic generator/analyzer and a protocol engine that triggers a waveform analyzer to analyze the signal waveform of a device under test at a predetermined point. Such a test system may offer improved capabilities such as a more selective and accurate measurement of complex signal waveforms, more automated measurements of waveforms pertaining to wireless communication data streams, and more rapid identification and measurement of waveforms corresponding to errored packets.

Abstract: Various embodiments select features from a feature space. In one embodiment, a set of training samples and a set of test samples are received. A first centered Gram matrix of a given dimension is determined for each of a set of feature vectors that include at least one of the set of training samples and at least one of the set of test samples. A second centered Gram matrix of the given dimension is determined for a target value vector that includes target values from the set of training samples. A set of columns and rows associated with the at least one of the test samples in the second centered Gram matrix is set to 0. A subset of features is selected from a set of features based on the first and second centered Gram matrices.

Abstract: Methods and systems to reduce the number of factors or variables that need to be considered in generating a function such as a prediction function. The methods and systems may involve receiving a first set of factors and a data set associated with the first set of factors, calculating an importance value of each factor in the first set of factors, and selecting, based on the importance values, a second set of factors. In some embodiments, the methods and systems also include generating the prediction function based on the data set and the second set of factors.

Abstract: Systems and methods are described herein for analyzing neural response data that can be assigned to multiple classes. The systems and methods begin with a set of training data from which optimal weight factors are derived. The derived weight factors are used in a classifier which is then applied to test data from test subjects. The classifier filters out the effects of less relevant data in the test data and provides a result in the form of probabilities associated with classes for the test data.

Abstract: Apparatus for optimizing the description of contents in a layout document is disclosed. The apparatus comprises: a parsing unit, for parsing the content of an original layout document to obtain text graphic unit data; an identification unit, for identifying text properties of each character of the text graphic unit data; a text node classification unit, for classifying characters of the text graphic unit data according to the text properties, and saving characters with the same text properties to the same text node along with the same text properties; a text content node classification unit, for, with respect to characters saved in each text node, saving characters on the same line or column. A terminal and a method for optimizing the description of contents in a layout document are disclosed.

Abstract: A signal processing device includes: a memory; and a processor coupled to the memory and configured to: detect a second feature value relating to a first feature value recognized to satisfy a recognition condition, from a second time series prior to a first time series of the first feature value in a times series of a feature value corresponding to an input signal, and change the recognition condition so that the second feature value is recognized as a class for recognizing the first feature value.

Abstract: An apparatus and a method are provided for learning a program with a large number of parameters. In one embodiment, a method not only distorts the input values, but also distorts some of the parameters in the program model. Such an approach not only forces the learned program to acquire parameter values to predict missing or desired data, but also to correct errors in the input data and the program parameters themselves, thereby rendering the learned program more resilient to overfitting and falling into local optima.

Abstract: Disclosed is a system and method for processing a connection request in an online service by a server corresponding to the online service. A connection request message that originates from a personalized account for a first user is sent to a personalized account for a second user and a certain threshold of access to posts related to the personalized account for the first user is provided to the personalized account for the second user for a certain period of time. An access to the posts related to the personalized account for the first user is otherwise accorded to authorized contacts of the personalized account for the first user on the online service.

Abstract: The disclosure provides an approach for estimating a state-space controller from a set of video frames depicting a motion of an entity. The approach includes incrementally optimizing parameters of the state-space controller and changing a structure of the state-space controller based on expanding subsets of the set of video frames. In one embodiment, a controller-estimation application greedily selects, at every stage of the incremental optimization, structure and parameters of the controller which minimize an objective function. In another embodiment, the controller-estimation application re-optimizes, after the incremental optimization, all parameters of the state-space controller based on all of the video frames.

Abstract: Described is a system for searching a continuous data stream for exact matches with a priori stored data sequences. The system includes a neural network with an input and an output layer. The input layer has one neuron for each possible character or number in the data stream, and the output layer has one neuron for each stored pattern. Importantly, the delays of the connections from input to output layer are engineered to match the temporal occurrence of an input character within a stored sequence. Thus, if an input sequence has the proper time gaps between characters, matching a stored pattern, then the delayed neural signals result in a simultaneous activation at the receiving neuron, which indicates a detected pattern. For storing a pattern, only one connection for each pair of input character and output neuron has to be specified resulting in sparse coding and quick storage.

Abstract: Methods and arrangements for handling queries for a discussion thread. A contemplated method includes: receiving a query; automatically classifying the query as subjective, objective or neither; and upon classifying the query as subjective or objective: calculating, for discussion threads of the query, at least one of: a subjectivity score and an objectivity score; determining a degree of relevance to the query of at least one of: the discussion threads, and at least one post in the at least one discussion thread; and ranking the discussion threads based on said calculating and determining. Other variants and embodiments are broadly contemplated herein.

Abstract: The present invention provides an improved, Internet-based system that seamlessly collects cardiovascular data from a patient before, during, and after a procedure for EP or an ID. During an EP procedure, the system collects information describing the patient's response to PES and the ablation process, ECG waveforms and their various features, HR and other vital signs, HR variability, cardiac arrhythmias, patient demographics, and patient outcomes. Once these data are collected, the system stores them on an Internet-accessible computer system that can deploy a collection of user-selected and custom-developed algorithms. Before and after the procedure, the system also integrates with body-worn and/or programmers that interrogate implanted devices to collect similar data while the patient is either ambulatory, or in a clinic associated with the hospital. A data-collection/storage module, featuring database interface, stores physiological and procedural information measured from the patient.

Abstract: A device (10) for processing events (4), including an identifier (8) identifying the event's type, and at least one parameter carrying information about a process, includes an event selector (20) and an event type recognizer (30). The device (10) is configured for receiving an event (4), providing the event (4) to the event selector (20), and providing the identifier (8) to the event type recognizer (30). The event selector (20) stores the provided event (4). The event type recognizer (30) determines, using at least one neural network unit, whether the identifier (8) corresponds to a type for which a subscription exists, and, if so, it causes the event selector (20) to transmit the event (4S) for processing by one or more applications. Furthermore, the device (10) is configured for allowing one or more types of event to be subscribed to. The invention also relates to methods for processing events (4).

Abstract: Embodiments of the invention provide a method comprising creating a structural description for at least one neurosynaptic core circuit. Each core circuit comprises an interconnect network including plural electronic synapses for interconnecting one or more electronic neurons with one or more electronic axons. The structural description defines a desired neuronal activity for the core circuits. The desired neuronal activity is simulated by programming the core circuits with the structural description. The structural description controls routing of neuronal firing events for the core circuits.

Abstract: Features are disclosed for facilitating content consumption and communication among a group of users. A content consumption group may be formed including any number of users, and content may be selected. Group members may consume roughly the same portion of the content at roughly the same time and share the consumption experience regardless of geographic location, user device, content format, on-demand consumption preferences, and the like. Policies may be defined or selected regarding the rate of content consumption, the communications and other inputs that may be submitted by group members, and the like. A shared content consumption management system may receive data from various user devices regarding each group member's current content consumption position, enforce group policies, and distribute group inputs. Group members may also communication in real time through various chats and other interactive features.

Abstract: A method of meta-learning includes receiving a prediction objective, extracting a plurality of subsets of data from a distributed dataset, generating a plurality of local predictions, wherein each local prediction is based on a different subset of the plurality of subsets of data and the prediction objective, combining the plurality of local predictions, and generating a final prediction based on the combined local predictions.

Abstract: In one embodiment, prior to similarity measure computation, concept expansion based on disjunctive normal form (DNF) decomposition and non-conventional reasoning is applied to an original ontology to generate an expanded ontology having the original concepts plus one or more pseudo concepts. As a result, the similarity measure computation can produce results that more accurately reflect a human point of view than convention techniques.

Abstract: Based on an event classification for an event of a cross-domain computing environment, a metric of a configuration item is obtained and used to isolate a causation of the event, wherein the event is a symptom or occurrence of an operational problem of at least one computing device in the cross-domain computing environment.

Abstract: Methods, and apparatus for performing methods, for selecting a classifier engine. Methods include, for two or more portions of a set of items of known classification, classifying members of each portion using a particular classifier engine; selecting a portion of the set of items whose classifications satisfy a first criteria; classifying members of the selected portion of the set of items using two or more classifier engines; and selecting a classifier engine whose classification of the selected portion of the set of items satisfies a second criteria.

Abstract: A method, computer system, and computer memory medium optimizing a transductive model Mx suitable for use in data analysis and for determining a prognostic outcome specific to a particular subject are disclosed. The particular subject may be represented by an input vector, which includes a number of variable features in relation to a scenario of interest. Samples from a global dataset D also having the same features relating to the scenario and for which the outcome is known are determined. In an embodiment, a subset of the variable features within a neighborhood formed by the samples are ranked in order of importance to an outcome. The prognostic transductive model is then created based, at least in part, on the subset, the ranking, and the neighborhood. The subset and the neighborhood are then optimized until the accuracy of the transductive model is maximized.

Abstract: A method of computerized content analysis that gives “approximately unbiased and statistically consistent estimates” of a distribution of elements of structured, unstructured, and partially structured source data among a set of categories. In one embodiment, this is done by analyzing a distribution of small set of individually-classified elements in a plurality of categories and then using the information determined from the analysis to extrapolate a distribution in a larger population set. This extrapolation is performed without constraining the distribution of the unlabeled elements to be equal to the distribution of labeled elements, nor constraining a content distribution of content of elements in the labeled set (e.g., a distribution of words used by elements in the labeled set) to be equal to a content distribution of elements in the unlabeled set.

Abstract: Apparatus and methods for learning in response to temporally-proximate features. In one implementation, an image processing apparatus utilizes bi-modal spike timing dependent plasticity in a spiking neuron network. Based on a response by the neuron to a frame of input, the bi-modal plasticity mechanism is used to depress synaptic connections delivering the present input frame and to potentiate synaptic connections delivering previous and/or subsequent frames of input. The depression of near-contemporaneous input prevents the creation of a positive feedback loop and provides a mechanism for network response normalization.

Abstract: A first device may receive a first password from a second device. The first password may be generated based on first time information and first location information identifying a geographic location of the second device. The first device may, determine a second password based on second time information and second location information identifying the geographic location of the second device. The first device may determine that the second device is located at the geographic location at a particular time when characters in the first password match characters in the second password, and may provide a service based on determining that the second device is located at the geographic location at the particular time.

Abstract: Bytecode is injected to create a source tracking object for a data object received from a data source and to record information associated with the data source into the source tracking object. Bytecode is injected to create a copy of the data object for a tracking event in an application program, to create a flow tracking object for the tracking event, and to record information associated with the tracking event into the flow tracking object as the tracking event processes the copy of the data object. Bytecode is injected to create a sink tracking object for outputting the copy of the data object to a data sink and to record information associated with the data sink into the sink tracking object. Bytecode is injected to output the source tracking object, the flow tracking object, and the sink tracking object as dynamic analysis of dataflow in the application program.

Abstract: The subject disclosure is directed towards providing data for augmenting an entity-attribute-related task. Pre-processing is preformed on entity-attribute tables extracted from the web, e.g., to provide indexes that are accessible to find data that completes augmentation tasks. The indexes are based on both direct mappings and indirect mappings between tables. Example augmentation tasks include queries for augmented data based on an attribute name or examples, or finding synonyms for augmentation. An online query is efficiently processed by accessing the indexes to return augmented data related to the task.

Abstract: Systems and methods for data classification and novel data class detection are provided. In one illustrative embodiment, a system or method for detecting a novel class includes receiving a data stream comprising a plurality of data points, and identifying a set of filtered outliers, in the plurality of data points, that are outside of a decision boundary. A cohesion and a separation for the set of filtered outliers may be determined. A novel class may be detected using the cohesion and the separation of the set of filtered outliers, and the novel class may include the set of filtered outliers.

Abstract: A system may include a model library configured to model a safety system, wherein the model library comprises a plurality of subsystem models, and each of the plurality of subsystem models is configured to derive a reliability measure. The system further includes a fault tolerance input and a maintenance policy input. The system further includes a dynamic risk calculation engine (DRCE) configured to use a user-defined set of the plurality of subsystem models, the fault tolerance input and the maintenance policy input, to derive a system risk for an apparatus.

Abstract: A method for classification of a newly arrived multidimensional data point (MDP) in a dynamic data uses multi-scale extension (MSE). The multi-scale out-of-sample extension (OOSE) uses a coarse-to-fine hierarchy of the multi-scale decomposition of a Gaussian kernel that established the distances between MDPs in a training set to find the coordinates of newly arrived MDPs in an embedded space. A well-conditioned basis is first generated in a source matrix of MDPs. A single-scale out-of-sample extension (OOSE) is applied to the newly arrived MDP on the well-conditioned basis to provide coordinates of an approximate location of the newly arrived MDP in an embedded space. A multi-scale OOSE is then applied to the newly arrived MDP to provide improved coordinates of the newly arrived MDP location in the embedded space.

Abstract: Disclose are methods for evaluating a user's interests and making gift recommendations using social media data. Interests and attributes of a user may be detected from social media content and products corresponding to the interests and attributes may be selected and presented as gift recommendations for the user. Methods are disclosed for resolving ambiguity as to interests reflected by textual data in social media content. Also disclosed are methods for inferring a user's interests from the interests of friends of the user.

Abstract: This disclosure relates to facilitating the association of structured content in a structured document with unstructured content in an unstructured document. The system described herein may be configured to facilitate the association by linking numeric instances in the structured document to corresponding numeric instances in the unstructured document. In some implementations, the system may be configured to link the numeric instances in the structured document to the corresponding numeric instances the unstructured document based on a uniqueness of the numeric instances in the structured document, structural information assigned to non-unique numeric instances, structural information assigned to unique numeric instances related to the non-unique numeric instances, unstructured contextual information related to non-unique numeric instances, and/or other information.

Abstract: An apparatus for detecting a malware in files includes an acquisition unit configured to obtain from a file system information about a first time point when an interested folder is created by the file system, and information about a second time point when an interested file is created in the interested folder by the file system, a candidate determination unit configured to determine whether the interested file is a candidate file to be subjected to a malware inspection, based on the information on the first and the second time point, and an inspection unit configured to perform the malware inspection on the interested file determined to be the candidate file for the malware inspection.

Abstract: Methods and apparatus consistent with the invention provide the ability to organize and build understandings of machine data generated by a variety of information-processing environments. Machine data is a product of information-processing systems (e.g., activity logs, configuration files, messages, database records) and represents the evidence of particular events that have taken place and been recorded in raw data format. In one embodiment, machine data is turned into a machine data web by organizing machine data into events and then linking events together.

Abstract: Object recognition apparatus and methods useful for extracting information from an input signal. In one embodiment, the input signal is representative of an element of an image, and the extracted information is encoded into patterns of pulses. The patterns of pulses are directed via transmission channels to a plurality of detector nodes configured to generate an output pulse upon detecting an object of interest. Upon detecting a particular object, a given detector node elevates its sensitivity to that particular object when processing subsequent inputs. In one implementation, one or more of the detector nodes are also configured to prevent adjacent detector nodes from generating detection signals in response to the same object representation. The object recognition apparatus modulates properties of the transmission channels by promoting contributions from channels carrying information used in object recognition.

Abstract: A corresponding point candidate determiner (108) determines whether plural correlation peaks appear, based on a correlation value calculated by a corresponding point determiner (107). In the case where the corresponding point candidate determiner (108) determines that plural correlation peaks appear, the corresponding point determiner (107) calculates a ratio between the correlation values as represented by the correlation peaks, determines one or more corresponding points, based on the calculated ratio, and notifies the determination result to an initial position setter (106). In the case where the corresponding point determiner (107) searches plural corresponding points, the initial position setter (106) sets an initial search position with respect to each of the corresponding points in a reference image of a layer immediately higher than a target layer.

Abstract: The invention relates to an apparatus for processing images by means of a series of user interactions. When processing an image, the user follows a series of interactions. Preferably, this is standardized to ensure reproducibility and accuracy. However, the series of interactions required from the user may be dependent on the needs of the user, the image being processed or even on the preferences of the user. The invention provides an apparatus which can deal with complex image processing requirements, providing both a standardized series of steps, or trail, in the image visualization process, and allowing the user to deviate from this standard trail if required. This accelerates and simplifies the interaction necessary when the user performs a known task on a different image.

Abstract: Certain aspects of the present disclosure support a technique for neural learning of natural multi-spike trains in spiking neural networks. A synaptic weight can be adapted depending on a resource associated with the synapse, which can be depleted by weight change and can recover over time. In one aspect of the present disclosure, the weight adaptation may depend on a time since the last significant weight change.

Abstract: Apparatus and methods for modulated plasticity in a spiking neuron network. A plasticity mechanism may be configured for example based on a similarity measure between post-synaptic activities of two or more neurons that may be receiving the same feed-forward input. The similarity measure may comprise a dynamically determined cross-correlogram between the output spike trains of two neurons. An a priori configured similarity measure may be used during network operation in order to update efficacy of inhibitory connections between neighboring neurons. Correlated output activity may cause one neuron to inhibit output generation by another neuron thereby hindering responses by multiple neurons to the same input stimuli. The inhibition may be based on an increased efficacy of inhibitory lateral connection.