Abstract: Systems and methods for providing remote approval of an image for printing are provided. One system includes a processing circuit in communication with an image capturing device that is configured to capture an image of a printed product. The processing circuit is configured to process the captured image into a processed image accurate to within a tolerance in a color space to indicate the visual appearance of one or more colors. The color space is a standardized color space, such as sRGB or CIELAB. The processing circuit is further configured to transmit the processed image to a display located remote from the image capturing device and to receive an input signal from a remote input device to allow a user to approve or reject the displayed processed image for printing on a print device.

Abstract: A specification part of an information processing device specifies, by using image data for a correction chart defining a plurality of patch regions having different color values, a target characteristic indicating a relation between the color value and a first colorimetric value of a first patch image as a laminated image of a special color image and a colored image that correspond to each of the patch regions formed by the device through the 2-path printing. A generation part of the device generates a correction table for correcting the color value so that a measured characteristic comes close to the target characteristic, the measured characteristic indicating a relation between the color value and a second colorimetric value of a second patch image as the laminated image corresponding to each of the patch regions formed by the device through the 1-path printing using the image data for a correction chart.

Abstract: An output apparatus including an acquisition unit configured to acquire document data having an output time limit and identification information used for identification; and an output unit configured to output the document data in a first output form of the identification information when the output time limit has elapsed, which is different from a second output form of the identification information before expiration of the output time limit.

Abstract: Related are a method and system for embedding information into encoding information. The method comprises the steps of first embedding the information into an embeddable image or a virtual image using a frequency domain embedding method, and then overlaying the embeddable image or the virtual image into a printed file in need of a variable code or a fixed code using a spatial domain processing method. In this way, the information not perceived by human eyes may be embedded into the encoding information using frequency domain and spatial domain transformation, the counterfeiting difficultly is extremely large, the cost is high, and the anti-counterfeiting purpose is achieved; and furthermore, the printing cost is not increased, thereby being beneficial to wide promotion and application.

Abstract: A system for tagging passenger baggage can include an indicia-reading device for reading decodable indicia associated with a boarding pass issued to a passenger, decoding the decodable indicia into a decoded message comprising boarding pass and baggage information for the passenger, and transmitting information of the decoded message. The system can also include a printer in communication with the indicia-reading device configured to receive the information of the decoded message transmitted from the indicia-reading device, and generate a baggage tag for baggage of the passenger based upon information of the decoded message received from the indicia-reading device.

Abstract: The present invention features compositions and methods useful in detecting counterfeit products and product diversion. The methods include packaging and indelibly marking products through an opening in their container and/or through a wall of the container that includes a hole therein. Unique identifiers are placed on the product and the container. In other methods, the product is not packaged within a container but is indelibly marked with first and second representations of a unique identifier, either or both of which can be machine-readable, human-readable, and/or at least partially randomized. An apparatus for carrying out the method of product marking is also disclosed.

Abstract: A method of power optimisation in an RFID device includes harvesting power from a radio-frequency excitation field using an antenna, powering a biometric authentication unit and an RFID communication module using the harvested power from the antenna; monitoring the voltage of the power supplied to the biometric authentication unit, and controlling a clock speed of a processing unit of the biometric authentication unit based on the monitored voltage by operating the processing unit at a higher clock speed when a high voltage level is detected and at a lower clock speed when a low voltage level is detected.

Abstract: A transaction card may comprise a first card component having an electrically conductive surface configured to receive an electrically applied coating. An electrically applied coating may be formed on the electrically conductive surface. The transaction card may be manufactured by forming a first card component having an electrically conductive surface configured to receive an electrically applied coating. The method may also include applying an electrically applied coating to the electrically conductive surface.

Abstract: A transaction card may comprise a first card component having an electrically conductive surface configured to receive an electrically applied coating. An electrically applied coating may be formed on the electrically conductive surface. The transaction card may be manufactured by forming a first card component having an electrically conductive surface configured to receive an electrically applied coating. The method may also include applying an electrically applied coating to the electrically conductive surface.

Abstract: This invention provides an insulated plug with an RFID tag including a main body and the RFID tag. The main body includes a conductive rod. The RFID tag includes a tag antenna and a tag chip connected at a feeding part of the tag antenna. The tag antenna includes a substrate and an antenna structure. The substrate has an installation hole, and the conductive rod passes through the installation hole and is fixed with the installation hole. The antenna structure is disposed at the substrate and includes a radiation part, a reflection part and a connection part. The radiation part is formed at one end of the substrate and has a feeding part. The reflection part is formed at the other end of the substrate and is closed. The connection part is disposed at the substrate and is electrically connected with the radiation part and the reflection part.

Abstract: A screen assembly may include a frame defining an aperture, a screen panel disposed within the aperture, the screen panel having a plurality of slots formed therethrough that extend between top and bottom surfaces of the screen panel, and an RFID tag disposed within a recess formed in an edge of the screen panel, the edge being between the top and bottom surfaces.

Abstract: A smart tag is attached on a vehicle body in a vehicle manufacturing process. The smart tag includes a position measurement transmitter for transmitting signals for measuring position of a vehicle body, a wireless communication transceiver for performing wireless communication, a position sensor for sensing data for calculating a position of the vehicle body, a memory for storing data including vehicle body information, a controller for controlling operation of the smart tag, and a battery for supplying electric power to components of the smart tag.

Abstract: An information processing apparatus includes a first artificial intelligence that outputs a first result by processing input information, and a second artificial intelligence that is different from the first artificial intelligence, and outputs a second result by processing the input information. Content of a process to be performed next is determined, based on results obtained by comparing the first result with the second result.

Abstract: In Multi-Policy Decision-Making (MPDM), many computationally-expensive forward simulations are performed in order to predict the performance of a set of candidate policies. In risk-aware formulations of MPDM, only the worst outcomes affect the decision making process, and efficiently finding these influential outcomes becomes the core challenge. Recently, stochastic gradient optimization algorithms, using a heuristic function, were shown to be significantly superior to random sampling. In this disclosure, it was shown that accurate gradients can be computed-even through a complex forward simulation—using approaches similar to those in dep networks. The proposed approach finds influential outcomes more reliably, and is faster than earlier methods, allowing one to evaluate more policies while simultaneously eliminating the need to design an easily-differentiable heuristic function.

Abstract: A method and a system are provided for predicting a non-linear relationship between a plurality of parameters in a deep neural network framework. The method comprises receiving, by an application server, a plurality of parameter values associated with the plurality of parameters. The method further comprises selecting, by the application server, an activation function based on a desired output. In an embodiment, the desired output is based on an industry type and an application area of the plurality of parameters. The method further comprises predicting, by the application server, the non-linear relationship between the plurality of parameters by modelling the deep neural network framework based on the selected activation function.

Abstract: Techniques for using data sets for a predictive model are described. According to various implementations, techniques described herein enable different data sets to be used to generate a predictive model, while minimizing the risk that individual data points of the data sets will be exposed by the predictive model. This aids in protecting individual privacy (e.g.

Abstract: Apparatuses and methods of manufacturing same, systems, and methods for generating a convolutional neural network (CNN) are described. In one aspect, a minimal CNN having, e.g., three or more layers is trained. Cascade training may be performed on the trained CNN to insert one or more intermediate layers until a training error is less than a threshold. When cascade training is complete, cascade network trimming of the CNN output from the cascade training may be performed to improve computational efficiency. To further reduce network parameters, convolutional filters may be replaced with dilated convolutional filters with the same receptive field, followed by additional training/fine-tuning.

Abstract: Cooperative neural networks may be implemented by providing an input to a first neural network including a plurality of first parameters, and updating at least one first parameter based on an output from a recurrent neural network provided with the input, the recurrent neural network including a plurality of second parameters.

Abstract: Cooperative neural networks may be implemented by providing an input to a first neural network including a plurality of first parameters, and updating at least one first parameter based on an output from a recurrent neural network provided with the input, the recurrent neural network including a plurality of second parameters.

Abstract: The technology disclosed proposes using a combination of computationally cheap, less-accurate bag of words (BoW) model and computationally expensive, more-accurate long short-term memory (LSTM) model to perform natural processing tasks such as sentiment analysis. The use of cheap, less-accurate BoW model is referred to herein as “skimming”. The use of expensive, more-accurate LSTM model is referred to herein as “reading”. The technology disclosed presents a probability-based guider (PBG). PBG combines the use of BoW model and the LSTM model. PBG uses a probability thresholding strategy to determine, based on the results of the BoW model, whether to invoke the LSTM model for reliably classifying a sentence as positive or negative. The technology disclosed also presents a deep neural network-based decision network (DDN) that is trained to learn the relationship between the BoW model and the LSTM model and to invoke only one of the two models.

Abstract: Systems and methods that include and/or leverage a neural network to approximate the steady-state performance of a turbine engine are provided. In one exemplary aspect, the neural network is trained to model a physics-based, steady-state cycle deck. When properly trained, novel input data can be input into the neural network, and as an output of the network, one or more performance indicators indicative of the steady-state performance of the turbine engine can be received. In another aspect, systems and methods for approximating the steady-state performance of a “virtual” or target turbine engine based at least in part on a reference neural network configured to approximate the steady-state performance of a “fielded” or reference turbine engine are provided.

Abstract: Techniques for a fixed-point back propagation implementation with advantages in speed, memory usage, and precision as compared with a floating-point implementation have hitherto been elusive. An example embodiment of a 16-bit fixed-point back propagation method that achieves a same accuracy as a double-precision, floating-point implementation, as measured by a word-error-rate (WER) of an acoustic adaptation application using one hour of audio data is disclosed. The WER for a speaker-independent model is 5.85%, compared with 5.34% for a double-precision floating-point implementation, and 5.33% for a 16-bit fixed-point implementation according to an example embodiment. Further, an average number of compute cycles for one backward propagation stage decreases from 166784 for a floating-point implementation to 30232 for a fixed-point implementation according to an example embodiment.

Abstract: Embodiments of the present invention include a system, computer-implemented method, and a computer program product. A non-limiting example of the method includes a processor utilizing a model having a plurality of parameters. The processor compares a current value of a model parameter to a prior value of the model parameter. Based at least in part on comparing the current value of the model parameter to the prior value of the model parameter, a determination is made that the model being utilized by the processor has changed. The current value of the model parameter is transmitted by the processor.

Abstract: This disclosure relates generally to data mining, and more particularly to system and method for mining data to generate actionable insights. In one embodiment, the method comprises receiving an input data and a target data, and detecting a defect in the target data using a neural network based predictive model and a scorecard rule table. The scorecard rule table comprises a plurality of scorecards corresponding to a plurality of nodes of the neural network. Each of the scorecards comprises a plurality of rules corresponding to a plurality of data variables in the input data. The method further comprises determining at least one root cause for the defect by determining at least one significant scorecard and at least one significant rule that contributed to the detection of the defect, and generating one or more actionable insights based on the at least one root cause.

Abstract: A computer-implemented method executed by at least one processor for training fast models for real-time object detection with knowledge transfer is presented. The method includes employing a Faster Region-based Convolutional Neural Network (R-CNN) as an objection detection framework for performing the real-time object detection, inputting a plurality of images into the Faster R-CNN, and training the Faster R-CNN by learning a student model from a teacher model by employing a weighted cross-entropy loss layer for classification accounting for an imbalance between background classes and object classes, employing a boundary loss layer to enable transfer of knowledge of bounding box regression from the teacher model to the student model, and employing a confidence-weighted binary activation loss layer to train intermediate layers of the student model to achieve similar distribution of neurons as achieved by the teacher model.

Abstract: Using training data, machine learning is performed to construct a learning model which is a non-linear function for discrimination or regression analysis (S2). A degree of contribution of each input dimension is calculated from a partial differential value of that function. Input dimensions to be invalidated are determined using a threshold defined by a Gaussian distribution function based on the degrees of contribution (S3-S5). Machine learning is once more performed using the training data with the partially-invalidated input dimensions (S6). A new value of the degree of contribution of each input dimension is determined from the obtained learning model, and the degree of contribution is updated using the old and new values (S7-S8). After the processes of Steps S5-S8 are iterated a specified number of times (S9), useful dimensions are determined based on the finally obtained degrees of contribution, and the machine-learning model is constructed (S10).

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 risk evaluation method is disclosed. A machine learning is conducted by using a neural network by inputting training data. A data distance corresponding to a permission level is calculated based on restoration data and the training data, the permission level being among a plurality of layers of the neural network, the restoration data being generated by using at least one weight of a plurality of permission level weights at the permission level, the plurality of permission level weights being among a plurality of weights of synapses at the plurality of layers, the plurality of weights being generated by the machine learning.

Abstract: A method and an apparatus to build a machine learning based network model are described. For example, processing circuitry of an information processing apparatus obtains a data processing procedure of a first network model and a reference dataset that is generated by the first network model in the data processing procedure. The data processing procedure includes a first data processing step. Further, the processing circuitry builds a first sub-network in a second network model of a neural network type. The second network model is the machine learning based network model to be built. The first sub-network performs the first data processing step. Then, the processing circuitry performs optimization training on the first sub-network by using the reference dataset.

Abstract: According to an embodiment, a network training device includes a first training unit that trains a first network that converts an input signal to a first signal, a second training unit that trains a second network that converts the first signal to a second signal, and a third training unit that trains a third network that converts the second signal to an output signal. The first training unit trains the first network as an encoder of a first autoencoder. The second training unit trains the second network by backpropagation by using a second signal for training corresponding to the first signal for training as supervised data. The second signal for training is generated by an encoder of a second autoencoder that encodes a third signal for training into the second signal for training, and decodes the second signal for training into the third signal for training.

Abstract: The technology disclosed proposes using a combination of computationally cheap, less-accurate bag of words (BoW) model and computationally expensive, more-accurate long short-term memory (LSTM) model to perform natural processing tasks such as sentiment analysis. The use of cheap, less-accurate BoW model is referred to herein as “skimming”. The use of expensive, more-accurate LSTM model is referred to herein as “reading”. The technology disclosed presents a probability-based guider (PBG). PBG combines the use of BoW model and the LSTM model. PBG uses a probability thresholding strategy to determine, based on the results of the BoW model, whether to invoke the LSTM model for reliably classifying a sentence as positive or negative. The technology disclosed also presents a deep neural network-based decision network (DDN) that is trained to learn the relationship between the BoW model and the LSTM model and to invoke only one of the two models.

Abstract: A method, system and computer-usable medium for using cognitive graph vectors to refine cognitive insights comprising storing data from a plurality of data sources within a cognitive graph via a cognitive inference and learning system; associating a first set of the data within the cognitive graph with a first cognitive graph vector of a plurality of cognitive graph vectors via the cognitive inference and learning system; associating a second set of the data within the cognitive graph with a second cognitive graph vector of the plurality of cognitive graph vectors via the cognitive inference and learning system; processing the data from the plurality of data sources to provide cognitive insights via the cognitive inference and learning system; and refining the cognitive insights based upon a limitation relating to one of the plurality of cognitive graph vectors via the cognitive inference and learning system.

Abstract: A computerized method comprising receiving, from a question answering system, a minimal answer value to a query submitted by a user. Also received are electronic documents based on the minimal answer value, and a document score value, associated with the query, for each of the electronic documents. The method comprises extracting entities and attributes from electronic documents, and for each computing one or more associated score value, and aggregating the document score value with the associated score values. The method comprises selecting some of entities and attributes based on the respective aggregated score value, thereby producing selected associated elements. The method comprises generating, using a computerized natural language (NL) generating system, a comprehensive NL answer, wherein the generating is based on the minimal answer value and the selected associated elements, and sending the comprehensive NL answer for presentation to the user.

Abstract: A set of profile parameters to characterize an unknown group of servers is computed. A set of known groups of servers is selected from a historical repository of known group of servers. A subset of known group is selected such that each known group in the subset has a corresponding similarity distance that is within a threshold similarity distance from the unknown group. A decision tree is constructed corresponding to a known group in the subset, by cognitively analyzing a usage of the set of profile parameters of the unknown group in the known group. Using the decision tree a number of problematic servers is predicted in the unknown group. When the predicted number of problematic servers does not exceed a threshold number, a post-prediction action is caused to occur on the unknown group, which causes a reduction in an actual number of problematic servers in the unknown group.

Abstract: Methods and systems are provided for assigning computational problems to be solved by compute nodes that have artificial intelligence problem-solving capability. A method includes receiving a computational problem to be solved. Node-related processing attributes of the compute nodes are used to determine which one or more of the compute nodes are capable of solving the computational problem. One or more of the compute nodes are selected to handle the computational problem based upon the determination.

Abstract: An online system generates, based on previously recorded content presentations, user value distributions for users of the online system. The online system also receives third party specifications from a third party system. Using this information, the online system generates a simulation for presenting content to users of the online system based on the third party specifications. For each iteration of the simulation, the online system randomly selects a user of the online system matching specifications, accesses the user value distribution for the randomly selected user, computes a selection probability of a successful content presentation to the randomly selected user, and simulates a content transmission based on the selection probability. The results of the simulation are reported to the third party system.

Abstract: Updating ground truth data in a security management platform is disclosed. One example is a system including at least one processor and a memory storing instructions executable by the at least one processor to receive, in a security management platform, event data relating to a plurality of events corresponding to operation of a computing arrangement in a current time interval, and computing ground truth data for the current time interval based on the received event data, and threat intelligence data from time intervals preceding the current time interval. A prediction model is applied to generate predictions for the current time interval based on the received event data. Ground truth data is re-computed for the time intervals preceding the current time interval based on a comparison of the generated predictions and the computed ground truth data.

Abstract: The factual accuracy of an event is verified. Event data is received by a computer, whereby the event data includes actor data related to at least one actor involved in the event and location data related to a location of the event. A factual scenario is created based on the event data. A cognitive reasoning and analysis of the event data is performed to derive inferences regarding the event and a time-sequenced series of inferences is composed based on the cognitive reasoning and analysis of the event data. Integrity of the event data is validated by comparing a data points from different sources and at least one flag is prompted when an instance of factual inconsistency is identified by the step of validating the integrity. A rendering of the event is generated based on the factual scenario and the time-sequenced series of inferences.

Abstract: Techniques for using different data sources for a predictive model are described. According to various implementations, techniques described herein enable different data sets to be used to generate a predictive model, while minimizing the risk that individual data points of the data sets will be exposed by the predictive model. This aids in protecting individual privacy (e.g., protecting personally identifying information for individuals), while enabling robust predictive models to be generated using data sets from a variety of different sources.

Abstract: An analysis device according to the present application includes an acquisition unit and a determiner. The acquisition unit acquires an evaluation value for evaluating an action taken by a user who has viewed an electronic page containing summary information of content. The determiner determines an improvement parameter preferable as a summary parameter to be used when the content is converted into the summary information, based on a summary parameter used in the conversion and the evaluation value acquired by the acquisition unit, by optimization of an unknown function.

Abstract: A computer-implemented method and system for optimizing user experience are disclosed. The method and system include determining a power profile of a device; determining historical behavior of at least one user and using a criterion based on the power profile of the device for checking the historical behavior of the at least one user for establishing a connection.

Abstract: Mechanisms are provided for modifying response of cognitive systems to user requests based on a determined knowledge level of the user and knowledge level of the concepts referenced in the cognitive system responses. The mechanisms receive a response to a user submitted request received from a client computing system and determine a first knowledge level of the user for a domain of the user submitted request. The mechanisms determine a second knowledge level associated with concepts referenced in the response and whether the first knowledge level is different from the second knowledge level. The mechanism, in response to the first knowledge level being different than the second knowledge level, modify content of the response to include concepts associated with the first knowledge level, to thereby generate a modified response. The modified response is then output to the client computing system associated with the user.

Abstract: A computer system for managing a multi-input adaptive decision making engine generates a first query object that requests a decision input relating to a relationship between a first variable and a second variable. The system receives from a first decision engine, a relationship indication that characterizes a relationship between the first variable and the second variable. Responsive to receiving the relationship indication, the system stores a first relationship attribute within a first variable dataset. The system also stores a second relationship attribute within a second variable dataset. The system then stores a decision attribute within a first decision engine dataset.

Abstract: The disclosed technology is generally directed to data corroboration, e.g., in IoT systems. In one example of the technology, receiving a first set of data over time from a first external device. A plausibility of the first set of data is determined based upon behavioral pattern matching. The first set of data is selectively authorizing as valid based at least upon the plausibility determination.

Abstract: Systems and methods for enabling automated log analysis with controllable resource requirements are provided. A training set for log pattern learning is generated based on heterogeneous logs generated by a computer system. An incremental learning process is implemented to generate a set of log patterns from the training set. The heterogeneous logs are parsed using the set of log patterns. A set of applications is applied to the parsed logs.

Abstract: Embodiments of the present invention are generally directed towards providing systems and methods for providing risk recommendation, mitigation and prediction. In particular, embodiments of the present invention are configured to allow for input of data related to known hazards to be interpreted and tracked or estimation of risk present in a variety of scenarios. Further embodiments of the present invention are configured to allow for predictive modeling and analysis of risk based on data as well as predictive behavior and other modeled information.

Abstract: Systems, computer products, and methods are described herein for improvements for identifying if an interaction between a user and an entity have been misappropriated. Instead of analyzing each interaction as the interactions are entered into between various users and the associated entities, a specific federated user model may be created for each user in order to predict the likelihood that interactions of the user may be misappropriated. In order to create the federated user model, a quantum optimizer may assign qubits to various inputs and analyze the inputs to create a federated user model that best predicts the user's interactions that may be misappropriated. As the inputs change, the quantum optimizer may be used to morph the federated user model in order to improve upon the ability of the specific federated user model in determining the likelihood that the user's interactions are misappropriated.

Abstract: In the present invention, a parametric oscillator 1 oscillates a plurality of pseudo spin pulses SPi having mutually an identical oscillation frequency by using parametric oscillation, an interaction implementing unit 5 performs feedback implementation of a magnitude and a sign of interaction related to each pseudo spin pulse SPi (the proportionality coefficient ?i+?Jij?j+?Kijk?j?k with respect to ?i) by using a tentative measurement result of oscillation phases ?i (tentative) of the plurality of pseudo spin pulses SPi, and a pseudo spin measuring unit 6 measures the pseudo spins ?i of the plurality of pseudo spin pulses SPi, based on a final measurement result of oscillation phases ?i (steady) of the plurality of pseudo spin pulses SPi.

Abstract: A calculation apparatus has: a dividing unit configured to divide a predetermined space including a substance of a calculation target into a plurality of regions; an electron wave function calculating unit configured to calculate an electron wave function for each of the regions obtained by the dividing by the dividing unit; and an all-electron wave function calculating unit configured to calculate an all-electron wave function by multiplying electron wave functions of the respective regions calculated by the electron wave function calculating unit.

Abstract: An embedding vector is the determined for a target user based on a weighted sum or the embedding vectors of entities the target user has interacted with in the past. Then, for each entity of a plurality of entities of the online system, a measure of similarity between the embedding vector of the user and the embedding vectors of the plurality of entities is determined. Based on the measure of similarity of each of the entities, the plurality of entities are ranked and one or more entities are selected to be presented to the user.