Abstract: Techniques are disclosed for performing optical character recognition (OCR) by assessing and improving quality of electronic documents to perform the OCR. For example a method for identifying information in an electronic document includes obtaining a reference image of the electronic document, distorting the reference image by adjusting different sets of one or more parameters associated with a quality of the reference image to generate a plurality of distorted images, analyzing each distorted image to detect the adjusted set of parameters and corresponding adjusted values, determining an accuracy of detection of the set of parameters and the adjusted values, and training a model based at least on the plurality of distorted images and the accuracy of the detection, wherein the trained model determines at least a first technique for adjusting a set of parameters in a second image to prepare the second image for optical character recognition.

Abstract: An illustrative example object detection system includes a camera having a field of view. The camera provides an output comprising information regarding potential objects within the field of view. A processor is configured to select a portion of the camera output based on information from at least one other type of detector that indicates a potential object in the selected portion. The processor determines an Objectness of the selected portion based on information in the camera output regarding the selected portion.

Abstract: According to an embodiment, a pattern recognition device recognizes a pattern of an input signal by converting the input signal to a feature vector and matching the feature vector with a recognition dictionary. The recognition dictionary includes a dictionary subspace basis vector for expressing a dictionary subspace which is a subspace of a space of the feature vector, and a plurality of probability parameters for converting similarity calculated from the feature vector and the dictionary subspace into likelihood. The device includes a recognition unit configured to calculate the similarity using a quadratic polynomial of a value of an inner product of the feature vector and the dictionary subspace basis vector, and calculate the likelihood using the similarity and an exponential function of a linear sum of the probability parameters. The recognition dictionary is trained by using an expectation maximization method using a constraint condition between the probability parameters.

Abstract: Tasks such as object classification from image data can take advantage of a deep learning process using convolutional neural networks. These networks can include a convolutional layer followed by an activation layer, or activation unit, among other potential layers. Improved accuracy can be obtained by using a generalized linear unit (GLU) as an activation unit in such a network, where a GLU is linear for both positive and negative inputs, and is defined by a positive slope, a negative slope, and a bias. These parameters can be learned for each channel or a block of channels, and stacking those types of activation units can further improve accuracy.

Abstract: A transaction card includes a card body, where the card body includes a surface with a first surface area. The surface of the card body includes private information that encompasses a second surface area of the surface, and the second surface area is less than the first surface area. The transaction card includes a reflective element that is applied to the surface of the card body, and includes a third surface area. The third surface area is based on the first surface area or the second surface area, and the third surface area enables the reflective element to reflect light away from the private information.

Abstract: Methods and apparatuses are described for generating a quick response (QR) grid that represents electronic data associated with a digital document. A server captures electronic data associated with a digital document, the electronic data comprising a plurality of key-value pairs. The server determines a total size of the electronic data and partitions the electronic data into two or more portions. The server generates a map of QR codes based upon the two or more portions of electronic data, each QR code in the map comprising a header, a footer, and a payload containing one of the two or more portions of electronic data. The server creates a QR grid using the map of QR codes. The server prints a physical document that corresponds to the digital document, the physical document including the created QR grid.

Abstract: A fluid treatment cartridge includes a housing having a fluid inlet and a fluid outlet with a treatment media contained within the housing. The fluid treatment cartridge includes a detection member comprising at least one closed electrically conductive loop having at least two spatially separate sections. Each of the sections generates a magnetic response when at least one section is electromagnetically excited. The magnetic response of each section is predetermined by the physical shape of the section and comprises at least one of a predetermined magnetic phase response and a predetermined magnetic amplitude response. The predetermined magnetic response of at least one other section of the closed electrically conductive loop corresponds to at least a one digit code.

Abstract: A method for securing an object from forgery involves a seal element having an antenna structure, an object to be secured, and at least one coupling element arranged or arrangeable at the object is supplied. The coupling element influences a value of an oscillating circuit parameter of the antenna structure when the antenna structure is arranged relative to the coupling element at the object. The seal element and the coupling element are arranged at the object such that a relative arrangement of the antenna structure to the coupling element at the object is fixed by which the value of the oscillating circuit parameter of the antenna structure arranged at the object is defined in dependence on the fixed relative arrangement, and serve as an authentication feature of the object. The value of the oscillating circuit parameter can be measured and associated with the object an authentication feature.

Abstract: A micro radio frequency identification tag for use on articles in an equipment identification and tracking system includes a substrate, an RFID chip, a power storage means, an antenna, and a conductive means. The substrate has a pair of surfaces. The RFID chip and power storage means are operatively retained on one surface. The antenna is operatively retained on the other surface of the substrate and acts as a conductive layer. The conductive means extends between the surfaces of the substrate to operatively connect the antenna to the RFID chip and power storage means.

Abstract: Mounting bracket apparatus to amplify electromagnetic field strengths associated with mountable RFID tags are disclosed. An example apparatus includes a mounting bracket having a central portion, a first field amplification arm extending from the central portion in a first direction, a second field amplification arm extending from the central portion in a second direction different from the first direction, and a mounting arm extending from the central portion in a third direction different from the first direction and the second direction. The example apparatus further includes a radio frequency identification (RFID) tag mounted to the central portion of the mounting bracket.

Abstract: The disclosure relates to a dual-interface integrated circuit (IC) card.

Abstract: An RFIC device including a resin block having a first surface, a second surface that faces the first surface, and a through-hole that extends through the first surface and the second surface. Moreover, the RFIC device includes an RFIC element that is embedded in the resin block and a coil antenna disposed in the resin block that is connected with the RFIC element and that has a central axis that extends from the first surface to the second surface. In addition, the through-hole extends inside the coil antenna.

Abstract: A device, system, and method is provided for storing a sparse neural network. A plurality of weights of the sparse neural network may be obtained. Each weight may represent a unique connection between a pair of a plurality of artificial neurons in different layers of a plurality of neuron layers. A minority of pairs of neurons in adjacent neuron layers are connected in the sparse neural network. Each of the plurality of weights of the sparse neural network may be stored with an association to a unique index. The unique index may uniquely identify a pair of artificial neurons that have a connection represented by the weight. Only non-zero weights may be stored that represent connections between pairs of neurons (and zero weights may not be stored that represent no connections between pairs of neurons).

Abstract: Embodiments of the present invention provide systems and methods for the fabrication of a crossbar array fabrication of resistive random access memory (RRAM) cells. The array structure contains large grain copper and its alloy or silver and its alloy. A metal cap and spacer are used to protect copper or silver from chemical modifications during memory cell patterning.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for receiving graph data representing an input graph comprising a plurality of vertices connected by edges; generating, from the graph data, vertex input data representing characteristics of each vertex in the input graph and pair input data representing characteristics of pairs of vertices in the input graph; and generating order-invariant features of the input graph using a neural network, wherein the neural network comprises: a first subnetwork configured to generate a first alternative representation of the vertex input data and a first alternative representation of the pair input data from the vertex input data and the pair input data; and a combining layer configured to receive an input alternative representation and to process the input alternative representation to generate the order-invariant features.

Abstract: Aspects herein describe new methods of determining optimal actions to achieve high-level goals with minimum total future cost. At least one high-level goal is inputted into a user device along with various observational data about the world, and a computational unit determines, though a method comprising backward and forward sweeps, an optimal course of action as well as emotions. In one embodiment a user inputs a high-level goal into a cell phone which senses observational data. The cell phone communicates with a server that provides instructions. The server determines an optimal course of action via the method of backward and forward sweeps, and the cell phone then displays the instructions and emotions to the user.

Abstract: An artificial neuron unit comprising one artificial neuron having at least one output port and at least one input port, and one memristor having two terminals; said unit being characterized in that it also comprises at least one current conveyor having two input ports X and Y, and one output port Z; and in which said memristor is connected by one of its terminals to the input port X of said current conveyor, said current conveyor is connected by its output port Z to an input port of said artificial neuron and said artificial neuron is connected by one of its output ports to the input port Y of said current conveyor or to another of said terminals of said memristor.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating document vector representations. One of the methods includes obtaining a new document; and determining a vector representation for the new document using a trained neural network system, wherein the trained neural network system has been trained to receive an input document and a sequence of words from the input document and to generate a respective word score for each word in a set of words, wherein each of the respective word scores represents a predicted likelihood that the corresponding word follows a last word in the sequence in the input document, and wherein determining the vector representation for the new document using the trained neural network system comprises iteratively providing each of the plurality of sequences of words to the trained neural network system to determine the vector representation for the new document using gradient descent.

Abstract: Multiple 3×3 convolutional filter kernels are used for approximating operations of fully-connected (FC) layers. Image classification task is entirely performed within a CNN based integrated circuit. Output at the end of ordered convolutional layers contains P feature maps with F×F pixels of data per feature map. 3×3 filter kernels comprises L layers with each organized in an array of R×Q of 3×3 filter kernels, Q and R are respective numbers of input and output feature maps of a particular layer of the L layers. Each input feature map of the particular layer comprises F×F pixels of data with one-pixel padding added around its perimeter. Each output feature map of the particular layer comprises (F?2)×(F?2) pixels of useful data. Output of the last layer of the L layers contains Z classes. L equals to (F?1)/2 if F is an odd number. P, F, Q, R and Z are positive integers.

Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.

Abstract: A design verification problem includes a design description and a property to be verified. Feature data is identified from the design verification problem and a result is predicted for the design verification problem based on the feature data. A plurality of verification engines is then orchestrated based on the prediction. Supervised machine learning may be used for the result prediction. Feature data and verification results from a plurality of training test cases are used to train a classifier to create a prediction model. The prediction model uses the feature data of the design verification problem to make a result prediction for the design verification model.

Abstract: There is provided a method, a system and a computer program product for supporting a decision making process. The system receives a decision model from a decision maker, the decision model used for determining a solution to a decision problem based on attributes and uncertainties of the decision problem. The decision problem includes information about a plurality of outcome vectors that represent all possible outcomes and the uncertainties associated with the decision problem. The system determines whether the received decision model can be solved without receiving any preference information from the decision maker. The system receives partially specified preference information from the decision maker if the received decision model cannot be solved without any preference information. The system solves the decision model with the partially specified preference information. The system recommends, based on the solution, one or more decisions to the decision maker.

Abstract: A mechanism is provided in a data processing system for tailoring question answering system output based on user expertise. The mechanism receives an input question from a questioning user and determines a set of features associated with text of the input question. The mechanism determines an expertise level of the questioning user based on the set of features associated with the text of the input question using a trained expertise model. The mechanism generates one or more candidate answers for the input question and tailors output of the one or more candidate answers based on the expertise level of the questioning user.

Abstract: Embodiments associate a relevant semantic data type (e.g., date) with incoming raw data (e.g., a column of digits) which lacks metadata. Assignment of semantic data type is inferred from a plurality of features. A first step determines a first feature comprising success rate in converting the raw data into various semantic data types. Then, alignment between observed/reference distributions of other features (e.g., data first digit, data length) is determined per-semantic data type. Total scores for each semantic data type are calculated from the combined features, and used as a basis for ranking the semantic data types. The total scores may reflect a weighting of the various features. In a second step, top-ranked semantic data types may be further differentiated from one another by applying additional features. User feedback regarding accuracy of semantic data type assignment, may be incorporated into training data used to modify the feature reference distributions.

Abstract: Methods, systems and computer program products for clustering pages into headline clusters are provided by collecting web data, identifying pages from the web data, tokenizing unique words in each page, recognizing unique entities in each page, detecting media links in each page, and constructing a plurality of vector representations of each page. A first dimension of each vector representation includes the unique words tokenized in each page, a second dimension of each vector representation includes the unique entities recognized in each page, and a third dimension of each vector representation includes the media links detected in each page. The vector representations are, in turn, clustered.

Abstract: Systems and methods of searching for related data sets are provided. Multivariate data sets can be input as queries into a data set search engine. According to one embodiment, the input data set is automatically reduced to a set of best fit data models of minimum complexity that represent the data set. The data model is then compared to other data models to not only identify similarity between the models, but also to identify the particulars of why the data models are related. Similar data model results can be analyzed to determine the quality of each returned data model based on an information scores. These results can be displayed graphically as a topographical map of nodes and edge. Each node can represent a data model and each edge can reflect the similarity between the nodes.

Abstract: The present invention relates to a method and apparatus for exploiting human feedback in an intelligent automated assistant. One embodiment of a method for conducting an interaction with a human user includes inferring an intent from data entered by the human user, formulating a response in accordance with the intent, receiving feedback from a human advisor in response to at least one of the inferring and the formulating, wherein the human advisor is a person other than the human user, and adapting at least one model used in at least one of the inferring and the formulating, wherein the adapting is based on the feedback.

Abstract: Embodiments of the present invention relate to apparatuses, systems, methods and computer program products for a technology configuration system. Specifically, the system typically provides operational data processing of a plurality of records associated with information technology operational activities, for dynamic transformation of data and evaluation of interdependencies of technology resources. In other aspects, the system typically provides technical language processing of the plurality of records for transforming technical and descriptive data, and constructing categorical activity records. The system may be configured to achieve significant reduction in memory storage and processing requirements by performing categorical data encoding of the plurality of records.

Abstract: Embodiments of the present invention relate to apparatuses, systems, methods and computer program products for a technology configuration system. Specifically, the system typically provides operational data processing of a plurality of records associated with information technology operational activities, for dynamic transformation of data and evaluation of interdependencies of technology resources. In other aspects, the system typically provides technical language processing of the plurality of records for transforming technical and descriptive data, and constructing categorical activity records. The system may be configured to achieve significant reduction in memory storage and processing requirements by performing categorical data encoding of the plurality of records.

Abstract: Quantum circuits and circuit designs are based on factorizations of diagonal unitaries using a phase context. The cost/complexity of phase sparse/phase dense approximations is compared, and a suitable implementation is selected. For phase sparse implementations in the Clifford+T basis, required entangling circuits are defined based on a number of occurrences of a phase in the phase context in a factor of the diagonal unitary.

Abstract: Systems and methods are provided for readout of a qubit. A readout resonator is coupled to a transmission line and a compound Josephson junction coupler couples the qubit to the readout resonator. A coupling controller controls the coupling strength of the compound Josephson junction coupler such that a coupling between the qubit and the readout resonator is a first value when a state of the qubit is being read and a second value during operation of the qubit.

Abstract: Embodiments are directed towards automatically learning user behavioral patterns when interacting with messages and based on the learned patterns, suggesting one or more predicted actions that a user might take in response to receiving subsequent message. One or more classifiers are trained and employed to predict one or more actions that a user might take in response to receiving the message. In one embodiment, the one or more predicted actions are provided suggested to the user as an action the user might take on the message. Messages may be rank ordered within a given suggested action based on a confidence level of the prediction.

Abstract: Data is received that include values that correspond to a plurality of variables. A score is then generated based on the received data and using a boosted ensemble of segmented scorecard models. The boosted ensemble of segmented scorecard models includes two or more segmented scorecard models. Subsequently, data including the score can be provided (e.g., displayed, transmitted, loaded, stored, etc.). Related apparatus, systems, techniques and articles are also described.

Abstract: A system ranks and/or recommends literary works based on information extracted from the text of the literary works. For example, the system may use information extracted from the text of a literary work to generate a graph representing the relationships of entities in the literary work. The system may identify sub-graphs in the graph, and generate a signature based on the values associated with the various sub-graphs. The system may generate signatures of a plurality of literary works. The system may then retrieve the signature of a literary work that was highly rated by a user, and compare the retrieved signature with other generated signatures using machine-learning algorithms to select literary works to recommend to the user.

Abstract: A computer-implemented method for selecting features for classification may include (1) generating a matrix X, a column vector Y, and a matrix Z from a training dataset that includes a plurality of samples with a plurality of features, (2) generating an augmented matrix from the matrix X, the column vector Y, and the matrix Z, (3) identifying one or more most-relevant features from the plurality of features by iteratively applying a sweep operation to the augmented matrix, and (4) training a classification model using the most-relevant features from the plurality of features rather than all of the plurality of features. Various other methods, systems, and computer-readable media may have similar features.

Abstract: Systems and methods may provide for partitioning a plurality of training samples into a first sequential list of centroids, removing one or more repeating centroids in the first sequential list of centroids to obtain a first reduced list of centroids and generating a set of Hidden Markov Model (HMM) parameters based on the first reduced list of centroids. Additionally, a plurality of detection samples may be partitioned into a second sequential list of centroids, wherein one or more repeating centroids in the second sequential list of centroids may be removed to obtain a second reduced list of centroids. The second reduced list of centroids may be used to determine a match probability for the plurality of detection samples against the set of HMM parameters. In one example, the reduced lists of centroids lack temporal variability.

Abstract: A method for determining the predictive value of a feature may include: (a) performing predictive modeling procedures associated with respective predictive models, wherein performing each modeling procedure includes fitting the associated model to an initial dataset representing an initial prediction problem; (b) determining a first accuracy score of each of the fitted models, representing an accuracy with which the fitted model predicts an outcome of the initial prediction problem; (c) shuffling values of a feature across observations included in the initial dataset, thereby generating a modified dataset representing a modified prediction problem; (d) determining a second accuracy score of each of the fitted models, representing an accuracy with which the fitted model predicts an outcome of the modified prediction problem; and (e) determining a model-specific predictive value of the feature for each of the fitted models based on the first and second accuracy scores of the fitted model.

Abstract: Aspects of the subject disclosure may include, for example, embodiments that comprise provisioning a target user profile and obtaining viewing history data. Further embodiments include generating a group of control rules according to the target user profile and training a machine learning application according to the viewing history data and the group of control rules. Additional embodiments include receiving a first indication that a first media content is to be presented to a target user. Also, embodiments include determining by the machine learning application, that the first media content does not conform to the group of control rules and providing a first notification that the first media content does not conform to the group of control rules. Other embodiments are disclosed.

Abstract: According to the present disclosure, time-sequential threshold data can be automatically detected by a server and thus can be compared with operation data in all of time domains. Therefore, it is not necessary for an operator to input threshold data by hand. Further, according to the present disclosure, it is possible to precisely detect an error of a machine or a defect of a product which has not been conventionally recognized at the time of setting a threshold (absolute value).

Abstract: Some embodiments provide a system that facilitates use of a question-and-answer system. During operation, the system determines a business value of a question submitted by a first user to the question-and-answer system. Next, the system prioritizes answering of the question by a second user in the question-and-answer system based on the business value.

Abstract: An enterprise compensation application enables different users to create corresponding sets of custom filters of interest, and then stores in a non-volatile storage, data indicating the corresponding custom filters created by each user. In response to receiving a request from a user for information related to a set of employees, the application identifies the set of custom filter created by the user (by examining the stored data), presents information related to the requested set of employees and also makes available the identified set of custom filters. On receiving an input indicating that the user has selected a custom filter from the set, the application determines a subset of employee as limited by the selected custom filter and then presents the information related to the subset to the user. Thus, the enterprise compensation application simplifies/supports compensation management for a large number of employees.

Abstract: Ensuring that a user's demographic data is correct so that billing statements may be sent to a correct address for collecting payment(s) from the user is a challenge many service providers face. Automatic information standardization and verification is provided. When a user's demographic information is inputted into an information system, address information is standardized into a standard format, a breadth of a verification to perform for the user is determined, and cross-matching the user's demographic information with information provided by one or more third party data sources is performed. Results may be provided in near real-time so that any inconsistencies may be corrected on the front-end and thus avoid unnecessary operation costs and improving billing and statement delivery.

Abstract: Various aspects of a system and method are disclosed for communicating vehicle repair data among a plurality of parties, wherein a data pump is employed to automate the extraction of vehicle repair data such as labor hours estimation data from a repair facility computer system for delivery to interested parties, including a rental vehicle service provider that provides replacement rental vehicles to drivers whose vehicles are undergoing repairs at repair facilities. A reservation management computer system operated by the rental vehicle service provider can thus use the received vehicle repair data to facilitate management of replacement rental vehicle reservations by its business partners, such as insurance companies.

Abstract: A travel search machine generates a trip object defined by a corresponding trip identifier. The trip object may have a corresponding trip data structure to which one or more search results may be assigned by a user. For example, the travel search machine may be configured to receive a trip identifier as a submission from a user device, generate a trip data structure corresponding to the trip identifier, and responsive to a received command from a user device, assign one or more search results to the trip data structure, such that reference to the trip data structure via the received trip identifier causes a presentation of at least some of the one or more search results assigned to the trip data structure.

Abstract: A data processing system receives location data points from computing devices. The system annotates the location data points with entities and determines a duration each of the computing devices was at corresponding entities. The system aggregates the location data points into a set of sequences based on the duration and the entities and stores the set of sequences in a data record. The system accesses the database record including a set of sequences generated from location data points received from computing devices. The system receives, from a computing device, a request for a location sequence that includes a query. The system identifies an attribute of the computing device. The system identifies a sequence based on the set of sequences using the query and the attribute. The system transmits the sequence for display on a display device.

Abstract: A system and method for mobile social networking within a target area are provided. The method provides for mobile social networking. The method includes receiving a social networking profile, and a target area. The social networking profile has at least one user preference. The method also includes broadcasting the social networking profile to one or more members of the social network within the target area. The method further includes searching within the target area for the one or more members having a preference that is the same or similar to the at least one user preference. The method additionally includes enabling contact with the one or more members having the same or similar at least one user preference.

Abstract: An apparatus and method for using a mobile computer device for graphically displaying and modifying information in a manner to enhance comprehension of the information and allowing for the mobile and decentralized management of information to be accomplished, wherein such information may be related to bed management and patient placement information and, furthermore, enabling the information of interest to be organized, sorted, and used in various useful and novel ways.

Abstract: A central server containing a database receives snowfall data from weather stations that are contained at a multitude of different sites within a defined geographical area. The central server stores the snowfall data in the database, correlating the data with various user accounts. For instance, the data is correlated with the account of the owner of the site from which the data was received, and with the accounts of landscape contractors whom the owner of the site has engaged to clear snow from his site. The central server provides alerts to various user accounts based on the snowfall data. For instance, the server provides alerts to site owners based on the snowfall at their sites, and to landscape contractors based on the snowfall at sites they are engaged to clear snow from.

Abstract: A method and apparatus for providing a backlogged computing work exchange are provided. In the method and apparatus, a computer system receives a request, whereby satisfaction of the request requires enqueuing computing work, The computer system determines a queued computing work quota of a plurality of queued computing work quotas for use in enqueuing the computing work and submits the request for execution, whereby the request is associated with a second client and the queued computing work quota of the plurality of queued computing work quotas is associated with a first client different from the second client.

Abstract: Automatically extracting and completing tasks associated with a communication is provided. In some examples, an application, such as a task management application, may generate nodes based on properties extracted from a communication, generate tasks based on the nodes, and construct a graph based on the nodes and the tasks. The task management application may also perform a prioritization of the tasks within the graph based on the properties of the nodes, order the tasks within the graph based on the prioritization of the tasks, and provide a task management interface to present the tasks within the graph. The task management application may also transmit the tasks within the graph to a task extraction engine of the task management application in response to a modification input executed on the graph.