Abstract: System, methods, and other embodiments described herein relate to semi-supervised training of a depth model for monocular depth estimation. In one embodiment, a method includes training the depth model according to a first stage that is self-supervised and that includes using first training data that comprises pairs of training images. Respective ones of the pairs including separate frames depicting a scene of a monocular video. The method includes training the depth model according to a second stage that is weakly supervised and that includes using second training data to produce depth maps according to the depth model. The second training data comprising individual images with corresponding sparse depth data. The second training data providing for updating the depth model according to second stage loss values that are based, at least in part, on the depth maps and the depth data.

Abstract: Embodiments for training a neural network are provided. A neural network is divided into a first block and a second block, and the parameters in the first block and second block are trained in parallel. To train the parameters, a gradient from a gradient mini-batch included in training data is generated. A curvature-vector product from a curvature mini-batch included in the training data is also generated. The gradient and the curvature-vector product generate a conjugate gradient. The conjugate gradient is used to determine a change in parameters in the first block in parallel with a change in parameters in the second block. The curvature matrix in the curvature-vector product includes zero values when the terms correspond to parameters from different blocks.

Abstract: A method for digital image segmentation is provided. The method comprises training a neural network for image segmentation with a labeled training dataset from a first domain, wherein a subset of nodes in the neural net are dropped out during training. The neural network receives image data from a second, different domain. A vector of N values that sum to 1 is calculated for each image element, wherein each value represents an image segmentation class. A label is assigned to each image element according to the class with the highest value in the vector. Multiple inferences are performed with active dropout layers for each image element, and an uncertainty value is generated for each image element. The label of any image element with an uncertainty value above a predefined threshold is replaced with a new label corresponding to the class with the next highest value.

Abstract: Individual computer diagnostic support (CDS) systems are coupled to a ‘global’ CDS system, each of the CDS systems using the same learning system or the same learning system technique. Training and testing cases from each of the individual CDS systems are provided to the global CDS system, and the global CDS system uses these training cases to produce learning system parameters based on the training cases. Having more training cases than any of the individual CDS systems, the parameters provided by the global CDS system offer a higher quality diagnostic output than any of the individual CDS systems. The learning system parameters at the global CDS system may be provided to each of the individual CDS systems, to update the parameters of the individual CDS systems' learning system. The global CDS may also refine and/or adjust the structure of the embodied learning systems.

Abstract: Provided is a computer system for estimating an absolute position of a photographed object by just photographing the object with a camera, a position estimation method, and a program. The computer system acquires an image obtained by photographing an object, acquires three-dimensional position data of a camera which photographed the object, and estimates an absolute position of the object on the basis of the three-dimensional position data of the camera. Further, the computer system enables the camera to be tilted a specified angle in a direction of the object, and estimates the absolute position of the object on the basis of the three-dimensional position data of the camera and the tilted specified angle. Moreover, the computer system stores the position of the object and an altitude at the position in association with each other, and estimates an altitude associated with the estimated position of the object.

Abstract: A computerized-system and method for generating a reduced-size superior labeled training-dataset for a high-accuracy machine-learning-classification model for extreme class imbalance by: (a) retrieving minority and majority class instances to mark them as related to an initial dataset; (b) retrieving a sample of majority instances; (c) selecting an instance to operate a clustering classification model on it and the instances marked as related to the initial dataset to yield clusters; (d) operating a learner model to: (i) measure each instance in the yielded clusters according to a differentiability and an indicativeness estimators; (ii) mark measured instances as related to an intermediate training dataset according to the differentiability and the indicativeness estimators; (e) repeating until a preconfigured condition is met; (f) applying a variation estimator on all marked instances as related to an intermediate training dataset to select most distant instances; and (g) marking the instances as related to

Abstract: Disclosed is a non-transitory computer readable medium storing computer program, in which when the computer program is executed by one or more processors. When the computer program is executed by one or more processors of a computing device, the computer program performs an operation for user drawing-based security authentication, and the operations may include: determining to transmit a first control signal to cause a user terminal to display a first drawing input display, which includes one or more subjects, if a lock display release signal is received from the user terminal; receiving a first drawing input information inputted in accordance with the first drawing input display from the user terminal; and determining whether to release the lock display of the user terminal by inputting the received first drawing input information to a drawing evaluation model.

Abstract: Aspects of the subject matter disclosed herein include methods, systems, and other techniques for training, in a first phase, an object classifier neural network with a first set of training data, the first set of training data including a first plurality of training examples, each training example in the first set of training data being labeled with a coarse-object classification; and training, in a second phase after completion of the first phase, the object classifier neural network with a second set of training data, the second set of training data including a second plurality of training examples, each training example in the second set of training data being labeled with a fine-object classification.

Abstract: A computer system, a game loading method thereof and a computer readable storage medium are provided. The computer system includes a first storage, a second storage and a processor. The first storage stores multiple game files of a game. The access rate of the second storage is faster than the first storage. The processor is coupled to the first and second storages. The processor performs the game, stores corresponding game files in the first storage into the second storage according to process of the game, and access the game files stored in the second storage to continue progress of the game. Accordingly, loading time of game scene can be reduced, so as to improve gaming experience.

Abstract: In response to receiving observed data of mixed observed variables, a mixed causality objective function, being suitable for continuous observed variables and discrete observed variables is determined, wherein the mixed causality objective function includes a causality objective function for continuous observed variables and a causality objective function for discrete observed variables and the fitting inconsistency is adjusted based on weighted factors of the observed variables. Then, the mixed causality objective function is optimally solved by using a mixed sparse causal inference, suitable for both continuous observed variables and discrete observed variables, using the mixed observed data under a constraint of a directed acyclic graph, to estimate causality among the observed variables.

Abstract: Embodiments of the present disclosure relate to a method and apparatus for outputting information. The method can include: acquiring an image of a to-be-inspected object; segmenting the image into at least one subimage; for a subimage in the at least one subimage, inputting the subimage into a pre-trained defect classification model to obtain a defect category corresponding to the subimage; and outputting defect information of the object based on a defect category corresponding to each subimage.

Abstract: An emotional wellness management system and methods of managing emotional wellness, to help people interactively and iteratively manage and improve their daily processes of emotional wellness. The system comprises storage coupled to a controller for capturing, storing, retrieving, processing, updating and displaying information related to a user's psychological condition comprising user affects, influencers, and actions. A user interface device, coupled to the controller, configured to have a plurality of interactive interfaces to capture user inputs of states of user affects and influencers, provides action links for accessing resources in the user interface device, also providing visual feedback. The controller is configured to interface with at least one controller from a support network via a communication link, and able to capture, store, retrieve, process, update and display information related to user's psychological condition.

Abstract: System, methods, and other embodiments described herein relate to improving the training of a driver during automated driving system mode. In one embodiment, a method includes generating, in association with a vehicle takeover and a maneuver by the driver, an automated motion plan associated with the maneuver. The method also includes determining if a difference parameter satisfies a threshold, wherein the difference parameter indicates a disparity between the maneuver by the driver in relation to the automated motion plan associated with the maneuver. The method also includes notifying, if the difference parameter does not satisfy the threshold, the driver that the vehicle takeover and the maneuver by the driver were unnecessary.

Abstract: A method and apparatus are provided that includes iteratively sampling candidates from medical records and evaluating whether ones of the candidates better explain a member from the medical records. The iterations replace the member with the candidates and depending on whether the candidates better explain the member from the medical records may be weighted in a next iteration.

Abstract: Methods and apparatus, including computer program products, implementing and using techniques for processing suspect duplicate records in a master data management system. A master data management module identifies two or more suspect duplicate records in the master data management system based on scores. A matching engine classifies the two or more suspect duplicate records, by comparing the scores against threshold values, into one of: a match, a non-match, and a possible match. The master data management module re-classifies the suspect duplicate records and adjusting the threshold values of the matching engine for classification of future records, in response to receiving, by a data stewardship client, a user input indicating an incorrect classification of the suspect duplicate records.

Abstract: A method, system, and non-transitory compute readable medium determining and discerning items with multiple meanings in a sequence of items including producing a distributed representation for each item of the sequence of items including a word vector and a context vector, partitioning the sequence of items into classes, for an item using a representative word vector of each class, calculating a cosine distance between the word vector of said item and the class representative vector, and producing a new sequence of items by modifying the distributed representation in the producing by replacing each occurrence of an item depending on the cosine distance calculated by the calculating.

Abstract: A system and method for operating a user receiving device includes a first user device having an identifier associated therewith. A mobile user device obtains the identifier and communicates the identifier associated with the first user receiving device to a second user receiving device. The second user receiving device receives and stores the first user profile settings from the first user receiving device and operates with the first user profile settings.

Abstract: This disclosure relates to method and system for generating cognitive security intelligence for detecting and preventing malwares. In one embodiment, the method includes monitoring instructions being executed by a processor of a computing system, determining events triggered and activities performed by the execution of the instructions, correlating the events and the activities to determine a sequence of events and activities, and mapping the sequence of events and activities with a topographical threat map to detect a pattern match corresponding to a malware. The topographical threat map is event and activity behavior map of a number of categories of malwares, and is built based on a cognitive analysis using deep learning which may also be enriched with external knowledge or historic knowledge. The method further includes effecting a remedial measure, upon detecting the pattern match, to prevent the malware by constructing remedial instructions to be executed by the processor.

Abstract: Authenticity of Artificial Intelligence (AI) results may be verified by creating, for an AI system, from a plurality of original inputs to form a plurality of original inference results, a plurality of original signatures of representative elements of an internal state of the AI system constructed from each individual original inference result of the plurality of original inference results. During deployment of the AI system, a matching of a plurality of deployment time inference results with a plurality of deployment time signatures, to the plurality of original signatures and the plurality of original inference results, may be verified.

Abstract: A method to dynamically analyze measurement data comprising measurement data sets as the measurement data is received and moved to a data warehouse. The program instructions may receive the measurement data and may extract first metadata from the measurement data. The program instructions may then extract and analyze measurement data points in the measurement data to determine if the measurement data points meet a first criteria and generate second metadata in response to determining that the measurement data points meet the first criteria. The program instructions may then provide the measurement data points, the first metadata and the second metadata to a data warehouse for storage. The analysis of the measurement data and creation of new metadata may be performed dynamically as the data is acquired and stored in the data warehouse.

Abstract: There is provided a system for computing a secure statistical classifier, comprising: at least one hardware processor executing a code for: accessing code instructions of an untrained statistical classifier, accessing a training dataset, accessing a plurality of cryptographic keys, creating a plurality of instances of the untrained statistical classifier, creating a plurality of trained sub-classifiers by training each of the plurality of instances of the untrained statistical classifier by iteratively adjusting adjustable classification parameters of the respective instance of the untrained statistical classifier according to a portion of the training data serving as input and a corresponding ground truth label, and at least one unique cryptographic key of the plurality of cryptographic keys, wherein the adjustable classification parameters of each trained sub-classifier have unique values computed according to corresponding at least one unique cryptographic key, and providing the statistical classifier, whe

Abstract: A method for inferring patterns in multi-dimensional image data comprises providing a recursive network of sub-networks with a parent feature node and at least two child feature nodes; wherein each sub-network is associated with a distinct subset of the space; configuring nodes of the sub-networks with posterior distribution component; receiving image data feature input at the final child feature nodes; propagating node activation through the network layer hierarchy in a manner consistent with node connections of sub-networks of the network and the posterior prediction of child nodes; and outputting parent feature node selection to an inferred output.

Abstract: A classification learning section executes training of a feature quantity extraction section and training of a classification section resulting from a comparison between an output generated when feature quantity data is inputted to the classification section and training data regarding a plurality of classes associated with a source domain training image. A dividing section divides feature quantity data outputted from the feature quantity extraction section in accordance with input of an image into a plurality of pieces of partial feature quantity data corresponding to the image including a feature map of one or more of the classes. A domain identification learning section executes training of the feature quantity extraction section resulting from a comparison between an output generated when partial feature quantity data corresponding to the image is inputted to a domain identification section and data indicating whether the image belongs to a source domain or to the target domain.

Abstract: Various embodiments of the teachings herein include a method for training and updating a backend-side classifier comprising: receiving, in a backend-device, from at least one vehicle, classification data along with a respective classification result generated by a vehicle-side classifier; and training the backend-side classifier using the classification data and, if available, a corrected respective classification result as annotation.

Abstract: A data analyzing device generates a diagram that shows a relationship between a first feature and an objective variable. The first feature is selected in accordance with an input of a user from among features having higher degrees of importance. The data analyzing device divides analysis target data into a plurality of clusters on the basis of values of the first feature, calculates a representative value of the objective variable of each of the clusters, extracts a second feature having a representative value of the objective variable, which is determined as having a significant difference relative to the representative value of the objective variable of the first feature, from at least one of the clusters. The data analyzing device generates a diagram that shows a relationship between the second feature and the objective variable.

Abstract: An information processing apparatus includes: a memory; and a processor configured to: execute genetic processing on class classification programs of a set of class classification programs; acquire a distance between each learning data and an identification boundary regarding evaluation identifiers created by using first class learning data belonging to a first class and second class learning data belonging to a second class according to the class classification program; calculate a statistic amount of a distribution of a distance to the identification boundary for each of the first class learning data and the second class learning data; define a fitness calculation equation based on the statistic amounts of the first class learning data and the second class learning data; calculate the fitness of the class classification program; and determine whether or not to replace the class classification program with one of class classification programs of the set depending on the fitness.

Abstract: In one embodiment, a management entity monitors for a change in a convergence rate of spatio-temporal compressive sensing measurements from a plurality of sensors in a sensor network operating according to a measurement matrix up to a halting criterion, and if the change is below a given threshold, determines whether the change is due to impulse noise or due to continued sensed measurements. If continued sensed measurements, the management entity initiates a single-dimensional compressive sensing in a spatial domain at regular time intervals, and identifies and tracks gradient clusters. In response to a change in joint spatio-temporal sparsity of tracked nodes of the gradient clusters, the management entity can then determine an updated measurement matrix based on the joint spatio-temporal sparsity of tracked nodes while satisfying one or more operating parameters, and directs at least certain sensors of the plurality of sensors to operate according to the updated measurement matrix.

Abstract: Medical images may be classified by receiving a first medical image. The medical image may be applied to a machine learned classifier. The machine learned classifier may be trained on second medical images. A label of the medical image and a measure of uncertainty may be generated. The measure of uncertainty may be compared to a threshold. The first medical image and the label may be output when the measure of uncertainty is within the threshold.

Abstract: A method is provided for forming a Deep Neural Network (DNN). The method includes quantizing deep learning data structures of the DNN into at least two modes using at least two scale factors, respectively. Each of the at least two modes corresponds to a respective one of the at least two scale factors. The method further includes identifying which of the at least two scale factors to use for a given one of the data structures based on a data distribution of the given one of the data structures. The quantizing step includes identifying when a tail of the given one of the data structures starts by (i) building a histogram of values in the given one of the data structures using successive bins; (ii) identifying a ratio of density between the successive bins; and (iii) checking whether the ratio of density is greater than a ratio of density threshold.

Abstract: Techniques are provided herein for creating well-balanced computer-based reasoning systems and using those to control systems. The techniques include receiving a request to determine whether to use one or more particular data elements, features, cases, etc. in a computer-based reasoning model (e.g., as data elements, cases or features are being added, or as part of pruning existing features or cases). Conviction measures are determined and inclusivity conditions are tested. The result of comparing the conviction measure can be used to determine whether to include or exclude the feature, case, etc. in the model and/or whether there are anomalies in the model. A controllable system may then be controlled using the computer-based reasoning model.

Abstract: Systems and methods are described to address shortcomings in a conventional conversation system via a novel technique utilizing artificial neural networks to train the conversation system whether or not to continue context. In some aspects, an interactive media guidance application determines a type of conversation continuity in a natural language conversation comprising first and second queries. The interactive media guidance application determines a first token in the first query and a second token in the second query. The interactive media guidance application identifies entity data for the first and second tokens. The interactive media guidance application retrieves, from a knowledge graph, graph connections between the entity data for the first and second tokens. The interactive media guidance application applies this data as inputs to an artificial neural network.

Abstract: A neural network training device according to an exemplary aspect of the present invention includes: a memory that stores a set of instructions; and at least one central processing unit (CPU) configured to execute the set of instructions to: determine a regularization strength for each layer, based on an initialized network; and train a network, based on the initialized network and the determined regularization strength, wherein the at least one CPU is further configured to determine the regularization strength in such a way that a difference between magnitude of a parameter update amount calculated from a loss function and magnitude of a parameter update amount calculated from a regularization term falls within a predetermined range.

Abstract: There is provided with an image identification apparatus. An extraction unit extracts a feature value of an image from image data using a Neural Network (NN). A processing unit identifies the image based on the feature value extracted by the extraction unit. The NN comprises a plurality of calculation layers connected hierarchically. The NN includes a plurality of sub-neural networks for performing processing of calculation layers after a specific calculation layer. Mutually different data from an output of the specific calculation layer are respectively inputted to the plurality of sub-neural networks.

Abstract: Provided is a system configured to determine and push adjustments to vehicle operations using machine-learning systems across multiple computing layers.

Abstract: A method for updating an object detector of an autonomous vehicle to adapt the object detector to a driving circumstance is provided.

Abstract: A detection modeling system for alerting to analytical model degradation has a processing device and a memory coupled to the processing device. The detection modeling system is configured to perform a distribution analysis on the selected detection model to determine a first health rating for the selected detection model, perform a survival analysis on the selected detection model to determine a second health rating for the selected detection model, generate an indicative score for the detection model based on the first health rating and the second health rating, and compare the indicative score to a threshold value and alert to model degradation based on the comparison.

Abstract: The present disclosure relates generally to techniques for enhancing recurrent neural networks (RNNs) implemented on an integrated circuit. In particular, approximations of activation functions used in an RNN, such as sigmoid and hyperbolic tangent, may be implemented in an integrated circuit, which may result in increased efficiencies, reduced latency, increased accuracy, and reduced resource consumption involved with implementing machine learning.

Abstract: Electronic sensing systems and methods are disclosed. The electronic sensing system (ESS) receive an olfactory product and one or more smell characteristics of the olfactory product are detected and extracted by identifying a headspace of the olfactory product. A comparison of the extracted smell characteristics with one or more smell characteristics associated with a historic training data stored in a database is performed and a match between the extracted smell characteristics and the one or more smell characteristics associated with the historic training data is determined using machine learning technique(s). Further, the ESS generates a report for the olfactory product comprising at least one of type of the consumable, name of the olfactory product, a status of the olfactory product, an age of the olfactory product, and a decaying index, and classifies the olfactory product into one or more categories based on the report and/or the historic training data.

Abstract: A method and apparatus include performing a first image analysis at a first resolution of an input tissue image. An uncertainty map is generated based on performing the first image analysis. A set of uncertain regions of the input tissue image are identified based on the uncertainty map. A second image analysis of the set of uncertain regions is performed at a second resolution of the tissue image that is greater than the first resolution. An analysis result is generated based on the first image analysis and the second image analysis.

Abstract: Techniques for employing user interfaces to output information indicative of events occurring in an inventory facility, and receive feedback from a human regarding the events are described herein. In one implementation, an event may take place in an inventory facility, such as a customer taking an item from an inventory location, returning an item to an inventory location, and so forth. An automated system of an inventory management system may process sensor data collected by sensors in the inventory facility to determine details of the event. In some examples, the inventory management system is unable to determine with a high level of confidence what occurred during the event. The inventory management system may provide the sensor data to a human associate through an associate interface, and receive input regarding details of the event from the human associate through the associate interface.

Abstract: Disclosed in some examples are methods, systems, and machine readable mediums which utilize volume to improve the ordering of search results for various information retrieval systems. This improves relevance as volume is a proxy for interest. As volume changes over time, the relevance of a particular result to a particular search query will increase or decrease over time.

Abstract: This disclosure relates to method and system for annotating tokens for natural language processing (NLP). In one embodiment, the method may include segmenting a plurality of corpus based on each of a plurality of instances, deriving a plurality of entities for each of the plurality of instances based on at least one of a machine learning technique or a deep learning technique, determining a word vector for each of the plurality of entities associated with each of the plurality of instances, and labelling a plurality of tokens for each of the plurality of instances. It should be noted that the plurality of tokens associated with the plurality of entities may be identified based on a frequency of each of the plurality of entities.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating responses using task-independent conversational systems are provided. In one example method, a response to a user text input is generated by updating a state of the conversation based on the user text input, generating a conversational (task-independent) output, and determining whether to provide a conversational response based on the conversational output, or to additionally generate a task-specific output.

Abstract: The present disclosure describes methods, systems, and computer program products for performing integration logic programming. One computer-implemented method includes receiving, by operation of a middleware system, first information in a first format corresponding to a first application, applying, by operation of the middleware system, one or more integration logic programming (ILP) patterns to the first information, the one or more ILP patterns representing application integration semantics using a logic programming language, generating, by operation of the middleware system, a second information in response to applying the one or more ILP patterns to the first information, and outputting, by operation of the middleware system, the second information in a second format corresponding to a second application.

Abstract: A method may include directing display of a dataset menu listing datasets representative of graphs. The method may include identifying features in the datasets as corresponding to nodes and edges. The method may include selecting local or global mapping to map categorical feature values to numeric values. Local mapping may be selected in response to a distribution of feature values not corresponding across different graphs. Global mapping may be selected in response to a distribution of the feature values corresponding across different graphs. The method may include directing display of configuration settings that indicate the selection between local and global mapping for training a classification model. The method may include obtaining selected configuration settings. The method may include providing the selected configuration settings and datasets to a machine learning backend, which may utilize the machine learning algorithm, datasets, and selected configuration settings to train the classification model.

Abstract: A system for use in monitoring an operation of a classification model in generating estimated labels for item records is described herein. The system receives a current labeling budget value including a number of trusted labels available for use in a labeling operation, determines a current selection probability for each item record included in an item list as a function of the current labeling budget value, selects a plurality of item records from the item list as a function of each corresponding current selection probability, and generates a sampling list including the selected item records. The system determines a risk measurement value associated with the classification model indicating an accuracy of the estimated labels as compared to trusted labels associated with the item records.

Abstract: A method for identifying a level of similarity between binary vectors includes storing, by a processor on a computing device, in each of a plurality of memory cells on the computing device, one of a plurality of binary vectors, each of the plurality of memory cells including a bitwise comparison circuit. The processor provides, to each of the plurality of memory cells, a received binary vector. Each of the bitwise comparison circuits determines a level of overlap between the received binary vector and the binary vector stored in the memory cell associated with the bitwise comparison circuit. Each of the comparison circuits that determines that the level of overlap satisfies a threshold provides, to the processor, an identification of the stored binary vector with the satisfactory level of overlap. The processor provides an identification of each stored binary vector satisfying the threshold.

Abstract: The present disclosure provides a method, a system, an apparatus and a computer-readable storage medium for sharing account resources. The method for sharing account resources comprises: acquiring an account of an original user satisfying a preset recycling condition; saving user information of the original user to a resource library, and adding the account of the original user to an allocatable account library; receiving a request for allocating an account from a requesting user, and allocating an account for the requesting user from the allocatable account library.

Abstract: A search query processing system that generates an ordered set of images that includes a search result. A location of a given image in the set of ordered images is based on a context of the search result and a pathway of physical progression of a subject. The search query processing system returns a set of search results based on a theme and a search result rule that relates to at least one of the following: (i) a manner in which the ordered set of search results are organized, or (ii) a scope of search results to be returned.

Abstract: Systems, computer program products, and methods are described herein for integration of a hexagonal convolutional neural network (H-CNN) within an image processing technical environment. The present invention is configured to initiate a hexagonal convolutional neural network (H-CNN); train the H-CNN using the first set of digital images; train the S-CNN in the image processing technical environment using the first set of digital images; classify a second set of digital images using the S-CNN using the second set of parameters; electronically receive an indication that the S-CNN has misclassified at least one of the second set of digital images; transform the at least one of the second set of digital images misclassified by the S-CNN as additional training data for the H-CNN; and re-train the H-CNN with the additional training data, wherein re-training the H-CNN further comprises modifying the first set of parameters for classification.