Abstract: An object recognition device 4 includes: a data reception unit 5 that creates observation data of respective sensors 1, 2 in accordance with sensor's detection data of an object in the surroundings of a host vehicle; an association processing unit 6 which, based on an association reference value, generates association data denoting a correspondence between the observation data and object data of a previous process cycle; and an updating processing unit 7 which, based on the association data, updates a state vector included in the object data of the previous process cycle, and updates the object data by including latest association data being the observation data having corresponded to the object data most recently, wherein the association processing unit 6 generates the association reference value using preferentially the latest association data of the same sensor as that of the observation data of a current process cycle.

Abstract: In order to process sensor data for a driver assistance system oriented towards the driver's comfort, sensor data that is sensed by a sensor device and describes objects is preprocessed such that a distinction is made between a driving zone and a non-driving zone, where the driving zone is designated as an object driving zone. The object driving zone is delimited by a boundary line. Since the sensor data is processed for a comfort-oriented driver assistance system, it does not have to describe the entire theoretical driving zone. Rather, the boundary line is used to delimit the driving zone within which the vehicle can normally be expected to drive. Based thereon, it is easy to determine an appropriate boundary line and significantly reduce the volume of data to be transmitted from the sensor device to a central control device of the comfort-oriented driver assistance system in order to describe the sensed objects.

Abstract: A vehicular control system includes a camera and a control having an image processor that processes captured image data to determine an object present in the forward field of view of the camera. The control is operable to determine an estimated time to arrival of another vehicle at a location that is in the projected path of travel of the equipped vehicle. Responsive to the received information being indicative of the state of a signal light at an intersection being green and responsive at least in part to (i) determination that the estimated time to arrival of the other vehicle is at least a threshold amount and (ii) determination that an object is not present in the projected path of travel of the equipped vehicle, the control may determine that it is safe for the equipped vehicle to proceed along the projected path of travel.

Abstract: A sensor for sensing biometric information includes a light emitting unit that emits a first light ray, a light receiving unit that receives a second light ray, where the second light ray includes a portion of the first light ray reflected by a body of a user, and an optical layer placed over the light emitting unit and the light receiving unit. The optical layer has a first surface facing the light emitting unit and the light receiving unit and a second surface opposite the first surface. The optical layer further includes an asymmetrical protrusion structure formed on the first surface or the second surface and including a plurality of asymmetrical protrusion units. The optical layer may further include a symmetrical protrusion structure formed on the first surface or the second surface opposite the asymmetrical protrusion structure and including a plurality of symmetrical protrusion units.

Abstract: An invention is disclosed for a real time video analytic processor that embodies algorithms and processing architectures that process a wide variety of sensor images in a fashion that emulates how the human visual path processes and interprets image content. spatial, temporal, and color content of images are analyzed and the salient features of the images determined. These salient features are then compared to the salient features of objects of user interest in order to detect, track, classify, and characterize the activities of the objects. Objects or activities of interest are annotated in the image streams and alerts of critical events are provided to users. Instantiation of the cognitive processing can be accomplished on multi-FPGA and multi-GPU processing hardwares.

Abstract: A method of determining a summation of pixel characteristics for a rectangular region of a digital image includes determining if a base address for a data element in an integral image buffer is aligned for an SIMD operation by a processor embedded in an electronic assembly configured to perform Haar-like feature calculations. The data element represents a corner of the rectangular region of an integral image. The integral image is a representation of the digital image. The integral image is formed by data elements stored in the integral image buffer. The data element is loaded from the integral image buffer to the processor when the base address is aligned for the SIMD operation. An offset data element of an offset integral image is loaded from an offset integral buffer when the base address is non-aligned for the SIMD operation. The offset data element represents the corner of the rectangular region.

Abstract: For image quality scoring of an image from a medical scanner, a generative model of an expected good quality image may be created using deep machine-learning. The deviation of an input image from the generative model is used as an input feature vector for a discriminative model. The discriminative model may also operate on another input feature vector derived from the input image. Based on these input feature vectors, the discriminative model outputs an image quality score.

Abstract: The subject matter of this specification can be implemented in, among other things, a method that includes identifying edges of a section of a document in a source image that includes at least one row of text. The method includes identifying characters in the document. The method includes identifying word portions. The method includes generating polynomials that approximate points of the characters within the word portions. The method includes generating a second polynomial that approximates the points of the characters of word portions. The method includes identifying a stretching coefficient of the row of text based on a length of the section between the edges relative to a length of the second polynomial. The method includes mapping portions of the source image along the row of text to new positions in a corrected image based on the second polynomial and the stretching coefficient.

Abstract: Scanners, methods, and computer storage media having computer-executable instructions embodied thereon that process variable sized objects with high package pitch on a moving conveyor belt are provided. The scanners include a substrate and a plurality of sensors attached to the substrate. The plurality of sensors forms an array of sensors having at least two or more rows of off-axis sensors. The sensors may include a one or more area array sensors. The arrays of sensors captures moving objects row by row and are optimized reduce object spacing on the conveyor belt. Additionally, the scanner having the array of sensor may process different objects having different heights at the same time. Accordingly, object throughput on the conveyor belt is increased by reducing minimum object gap (e.g., processing of “no gap” or non-singulated objects).

Abstract: Systems and methods for recognition of unreadable characters on printed circuit boards. In some embodiments, a method for recognizing characters can be utilized for recognition of damaged characters on a printed circuit board. The method can include obtaining a digital image for each of a plurality of characters on the printed circuit board. The method can further include dividing each digital image into an array of regions. The method can further include generating a data structure from the arrays of the digital images. The data structure can include gradient features based on stroke shapes on small distances, structural features based on stroke trajectories on extended distances, and concavity features based on stroke relationships.

Abstract: Systems, devices, and methods for monitoring items in a defined physical area can include a primary camera configured to detect a region of interest within a defined physical area and the coordinates of the region of interest in the defined physical area. A plurality of secondary cameras can positioned throughout a defined physical area. One of the secondary cameras can be selected to capture an image of a region of interest based on the coordinates of the region of interest.

Abstract: There are provided an environment recognition device and an environment recognition method. The environment recognition device obtains luminances of a target portion in a detection area of a luminance image, assigns a color identifier to the target portion according to the luminances of the target portion, based on association between a color identifier and a luminance range retained in a data retaining unit, and groups target portions assigned one of one or more color identifiers associated with a same specific object, and of which position differences in the width direction and in the height direction are within a predetermined range, based on association between the color identifier and the luminance range retained in the data retaining unit.

Abstract: An intelligent automatic license plate recognition (IALPR) system implements technical solutions that improve the accuracy of automatic license plate recognition. The IALPR analyzes an image of a vehicle proximate to a toll collection point using optical character recognition (OCR), and determines candidate license plate identifications based, at least in part, on the corresponding OCR confidence level. The IALPR can also perform fingerprinting for candidate license plate images and matching analysis with a knowledge base, resulting in additional confidence levels. The IALPR can also perform behavioral analysis on the candidate license plate identifications, including trip context analysis, historical behavioral analysis, or other analytics. The IALPR can generate an overall confidence level for the candidate license plate identifications responsive to the OCR and vehicle fingerprint confidence levels and the behavioral analysis.

Abstract: In various example embodiments, a system and method are provided for automated estimation of a saliency map for an image based on a graph structure comprising nodes corresponding to respective superpixels on the image, the graph structure including boundary-connecting nodes that connects each non-boundary node to one or more boundary regions. Each non-boundary node is in some embodiments connected to all boundary nodes by respective boundary-connecting edges forming part of the graph. Edge weights are calculated to generate a weighted graph. Saliency map estimation comprises bringing respective nodes for similarity to a background query. The edge weights of at least some of the edges are in some embodiments calculated as a function of a geodesic distance or shortest path between the corresponding nodes.

Abstract: Systems, methods, and non-transitory computer-readable media can acquire an image that depicts at least one character. A set of pixels, within the image, through which the at least one character is depicted can be identified. At least one linear portion, within the image, can be identified based on the set of pixels. For each sub-portion within the at least one linear portion, a respective first confidence score representing a respective first likelihood that a respective sub-portion depicts the at least one character can be determined.

Abstract: Object detection and classification across disparate fields of view are provided. A first image generated by a first recording device with a first field of view, and a second image generated by a second recording device with a second field of view can be obtained. An object detection component can detect a first object within the first field of view, and a second object within the second field of view. An object classification component can determine first and second level classification categories of the first object. A data processing system can create a data structure indicating a probability identifier for a descriptor of the first object. An object matching component can correlate the first object with the second object based on the descriptor of the first object, the probability identifier for the descriptor of the first object, or a descriptor of the second object.

Abstract: A method for recognizing an object in a video stream may include receiving a video stream from a video source, the video stream comprising a plurality of video frames. The method may also include selecting at least one video frame from the video frames according to a frame selection rate. The method may also include partitioning the selected video frame into a first plurality of image blocks. The method may also include recognizing, out of the first plurality of image blocks, a second plurality of image blocks which comprise an image of an object, the recognition being based on an image recognition parameter determined by a machine-learning algorithm. The method may also include determining that at least one of the second plurality of image blocks corresponds to the object based on a likelihood metric, the likelihood metric being determined by the processor based on at least the frame selection rate. The method may further include displaying, on a display, information identifying the object.

Abstract: The current document is directed to automated methods and systems, controlled by various constraints and parameters, that identify contours in digital images, including curved contours. Certain of these parameters constrain contour identification to those contours in which the local curvature of a contour does not exceed a threshold local curvature and to those contours orthogonal to intensity gradients of at least threshold magnitudes. The currently described methods and systems identify seed points within a digital image, extend line segments from the seed points as an initial contour coincident with the seed point, and then iteratively extend the initial contour by adding line segments to one or both ends of the contour. The identified contours are selectively combined and filtered in order to identify a set of relevant contours for use in subsequent image-processing tasks.

Abstract: Techniques for weather information extraction using image data are described herein. In accordance with the present disclosure, economical weather data collection devices may be installed in any places on the earth, and form a dense network of weather data collection devices. Preferably, these weather data collection devices include image capture components that may capture series of sequential images over time (i.e., image streams) from any particular locations. The disclosed techniques include extracting a sky portion from a series of time-sequenced images. The extracted sky portion may be used for determining cloud coverage, a sun track, and so on, thereby enabling to provide accurate weather forecast as well as other weather data mining abilities.

Abstract: An imaging apparatus includes a first reset signal line which is commonly connected to multiple first comparator circuits and through which a first reset signal to reset a threshold value of each of the multiple first comparator circuits is transmitted, a second reset signal line which is commonly connected to multiple second comparator circuits and through which a second reset signal to reset a threshold value of each of the multiple second comparator circuits is transmitted, and a shield line. The distance between the first reset signal line and the shield line and the distance between the second reset signal line and the shield line are smaller than the distance between the first reset signal line and the second reset signal line.

Abstract: The present disclosure provides a method performed at a computing device for recognizing an image's content. The method includes: extracting one or more features from an image to be recognized; comparing the features of the image with a set of image classifiers and obtaining a probability value for each image classifier; selecting, from the set of image classifiers, at least one image classifier as a target image classifier according to the probability value of the image classifier; determining a degree of similarity between each image and the image to be recognized, and selecting, from the target image classifier, multiple images as target images when their respective degrees of similarity with the image to be recognized exceed a predefined threshold; and labeling, the image to be recognized according to a class label corresponding to the target image classifier and entity labels corresponding to the target images in the target image classifier.

Abstract: In one aspect, the present disclosure implements a method of ranking images in real-time as the images are being received. In this regard, the method comprises receiving a first and a second images from end users. Then, the first and second images are made available to two or more human annotators from network accessible computing devices. The method provided by the present disclosure then receives designations from each of the two or more human annotators regarding whether the first or second image is preferred. From the received input, a determination is made, in the aggregate, whether the two or more human annotators preferred the first or second image. If the two or more human annotators preferred the first image, the method allocates a rank to the first image that is higher than the second image. On the other hand, if the two or more human annotators preferred the second image, the method allocates a rank to the second image that is higher than the first image.

Abstract: Methods and systems for testing base text direction (BTD) include receiving one or more images captured by an end-user system. Each of the one or more images displays respective text test case information. Each of the one or more images is compared to a respective reference image associated with a respective text test case. It is determined whether the end-user system produces BTD errors based on the comparison in accordance with one or more BTD error rules.

Abstract: Provided is a method of spatially referencing a plurality of images captured from a plurality of different locations within an indoor space by determining the location from which the plurality of images was captured. The method may include obtaining a plurality of distance-referenced panoramas of an indoor space. The distance-referenced panoramas may each include a plurality of distance-referenced images each captured from one position in the indoor space and at a different azimuth from the other distance-referenced images, a plurality of distance measurements, and orientation indicators each indicative of the azimuth of the corresponding one of the distance-referenced images. The method may further include determining the location of each of the distance-referenced panoramas based on the plurality of distance measurements and the orientation indicators and associating in memory the determined locations with the plurality of distance-referenced images captured from the determined location.

Abstract: A method, executed by a computer, includes receiving, for a cluster, a request to create a new container host, wherein the cluster comprises a plurality of container hosts having a corresponding plurality of local repositories, creating the new container host, selecting an image for the new container host according to one or more host preferences, wherein the image is stored in an image location, and copying the image from the image location to the local repository of the new container host. A computer system and computer program product corresponding to the above method are also disclosed herein.

Abstract: According to exemplary methods of training a convolutional neural network, input images are received into a computerized device having an image processor. The image processor evaluates the input images using first convolutional layers. The number of first convolutional layers is based on a first size for the input images. Each layer of the first convolutional layers receives layer input signals comprising features of the input images and generates layer output signals that include signals from the input images and ones of the layer output signals from previous layers within the first convolutional layers. Responsive to an input image being a second size larger than the first size, additional convolutional layers are added to the convolutional neural network. The number of additional convolutional layers is based on the second size in relation to the first size. The additional convolutional layers are initialized using weights from the first convolutional layers.

Abstract: A method for evaluating quality of tone-mapping image based on exposure analysis is provided, which explores the exposure properties on each area of the high dynamic range image utilizing the pre-exposure method and divides the high dynamic range image into three parts of an easy overexposed area, an easy underexposed area and an easy natural-exposed area, wherein different quality characteristics are extracted in different areas, which is capable of ensuring that the follow-up quality characteristic extraction is more targeted. The present invention takes the difference of distortion between the tone-mapping image and the conventional image into account, and extracts image characteristics such as the abnormal exposure rate, the underexposed residual energy, the overexposed residual energy and the exposure color index, so as to accurately reflect the quality degradation of the tone-mapping image.

Abstract: A camera system mounted on a vehicle includes a first substrate including an image sensor that generates image information by photoelectric conversion and a first communication unit, and a second substrate including a second communication unit for performing wireless communication with the first communication unit and a first information processing section at least capable of recognition processing for recognizing a situation outside the vehicle based on the image information acquired via the second communication unit.

Abstract: The disclosure discloses a tape printer including a data receiving portion, a display control portion, and a print control portion. The data receiving portion is configured to receive talk data containing plural pieces of speech related data along a time series, the speech related data including speech display texts from each of a first and a second speaker. The display control portion is configured to control the display device so that the plural pieces of speech related data is arrayed and displayed in order of the time series along a tape length direction, and first and second speech related data respectively in relation to the first and second speaker contained in the talk data are displayed in mutually different forms. The print control portion is configured to control a printing head to form a plurality of print objects corresponding respectively to the plural pieces of speech related data.

Abstract: A method of controlling a printer is described, for printing a pattern from a first row of fluid ejection nozzles and a second row of fluid ejection nozzles in a multi-pass printing mode. The first and second rows of fluid ejection nozzles eject fluid of a first type and fluid of a second type, respectively. The method comprises: assigning respective parts of the pattern to be printed to the first and second rows of fluid ejection nozzles; applying a first mask to the first row of said ejection nozzles and a second mask to the second row of fluid ejection nozzles for printing with selected nozzles of each of the rows of fluid ejection nozzles during each pass; wherein the first mask comprises a mesa portion and the second mask comprises a mesa portion wherein the mesa portion of the first mask includes at least a first peak and the mesa portion of the second mask includes at least a second valley, the first peak overlapping with the second valley.

Abstract: A print control apparatus includes an acquisition unit and a setup execution unit. The acquisition unit acquires, from a portable terminal, setting of an apparatus condition of an image forming apparatus that performs printing on continuous paper and of a print start time at which the image forming apparatus starts the printing. The setup execution unit starts a setup process for the image forming apparatus such that the setup process is completed by the print start time on the basis of the setting of the apparatus condition acquired by the acquisition unit. The setup process is performed for the image forming apparatus to perform the printing.

Abstract: A smart card read/write method is performed at a terminal, including: sensing a touch event of a smart card, and obtaining an application identifier corresponding to the touch event; searching for a third-party application link corresponding to the application identifier, and capturing and displaying a web page corresponding to the third-party application link, the web page comprising a function menu and an instruction script corresponding to options in the function menu being preselected from a preset standard script library; obtaining an option triggered in the function menu on the web page, and sending a smart card control request to a platform application server by executing an instruction script corresponding to the triggered option; and receiving a smart card control instruction returned by the platform application server, and invoking a corresponding interface function according to the smart card control instruction to read/write the smart card.

Abstract: A holder for cards providing RFID protection is disclosed herein. The holder comprises multiple sheaths, where each sheath has a card position adjacent a protective assembly and a means for holding the card adjacent the protective assembly. Each protective assembly comprises a conductive layer and an absorbing layer adjacent the card position. The sheaths are hingedly connected to enable the user to select a single card for desired use without the need to remove the card from the holder. Once the desired card read has been completed, the cards within the holder are shielded from unauthorized or malicious card reads.

Abstract: A Radio Frequency Identification (RFID) tag according to one embodiment includes a housing configured for coupling to an object, control circuitry coupled to the housing, a first power source for providing power to the control circuitry, a secondary power source physically coupled to the first power source that generates energy from light for recharging the first power source, and a memory for storing information.

Abstract: A Radio Frequency Identification (RFID) tag according to one embodiment includes a housing configured for coupling to an object, control circuitry coupled to the housing, and a memory for storing information, the information including a service history of the object.

Abstract: Electronic badges are indirectly tracked by detecting, by a badge communicator on a select industrial vehicle of a fleet of industrial vehicles, the presence of an electronic badge and performing a badge logging transaction in response to detecting the electronic badge. The badge logging transaction includes receiving, by the badge communicator, a badge identifier transmitted by the detected electronic badge. The badge logging transaction also includes determining, by the badge communicator, an offset measurement of the electronic badge relative to the select industrial vehicle, electronically determining a vehicle location of the select industrial vehicle, and identifying a badge location based upon the determined vehicle location and the measured offset. The badge logging transaction can also include generating a time stamp, and wirelessly communicating a badge locator message to a remote server, the badge locator message including the badge identifier, the badge location, and the timestamp.

Abstract: A method and system for transacting with a removable marking element is disclosed. A removable marking element including credentials can be associated with an account. A user can activate and manage the account via a mobile device. The mobile device can access the account by providing a product identifier. A product identifier may be provided in removable marking element packaging. For example, the product identifier may be encoded in a machine readable code on the packaging.

Abstract: The invention relates to a method for producing a module having an electronic chip including metallisations which are accessible from a first side of the metallisations and an integrated circuit chip which is arranged on the second side of the metallisations, opposite the first side. The method comprises the step of forming electrical interconnection elements which are separate from the metallisations, directly connecting the chip, and are arranged on the second side of the metallisations. The invention also relates to a module corresponding to the method and to a device comprising said module.

Abstract: A badge of the type comprising a substrate with a top side and a bottom side, an adhesive disposed on the bottom side for adhering the badge to a person, and a visually discernible material disposed on the top side for providing information, has a wireless device carrying first information secured directly or indirectly to said substrate. The visually discernible material comprises a first portion of visually discernible material and a second portion of visually discernible material. The first portion of visually discernible material is positioned, configured and dimensioned to communicate humanly perceptible and humanly readable second information. The second portion of visually discernible material carries third information encoded within the second portion of the visually discernible material and is positioned, configured and dimensioned to be scanned by an optical device in order to the read said third information encoded within the second portion of the visually discernible material.

Abstract: A system for controlling an industrial vehicle comprises an information linking device, a badge communicator, an operator badge, and a controller. The controller controls the industrial vehicle operating state by identifying that an operator possessing the operator badge has approached the industrial vehicle, communicating with the server via the information linking device to authenticate the operator as authorized to operate the industrial vehicle, and pairing the operator badge with the industrial vehicle upon determining that the operator is authorized to operate the industrial vehicle. Moreover, the controller controls the industrial vehicle operating state by controlling the industrial vehicle based upon a location of the operator badge relative to the industrial vehicle.

Abstract: Methods, systems, apparatuses, and computer program products are provided for altering the behavior of an electronic personal assistant based on a situation associated with a mobile device. A situation is sensed with a plurality of sensors to generate sensor data. A situation score is calculated based on the sensor data. Behavior of an electronic personal assistant is altered based on the calculated situation score. In one aspect, the situation is a driving situation in which a driver drives a vehicle on a roadway. In such case, a driving situation score is calculated based on the sensor data, and behavior of the electronic personal assistant is altered based on the calculated driving situation score, such as suspending interactions by the electronic personal assistant with the driver to avoid the driver being distracted.

Abstract: Mechanisms are provided for implementing a proximity based candidate answer pre-processor engine that outputs a sub-set of candidate answers to a question and answer (QA) system. The mechanisms receive a lexical answer type (LAT) and an entity specified in an input natural language question as well as an ontology data structure representing a corpus of natural language content. The mechanisms identify a set of candidate answers having associated nodes in the ontology data structure that are within a predetermined proximity of a node corresponding to the entity, and a sub-set of candidate answers in the set of candidate answers having an entity type corresponding to the LAT. The mechanisms output, to the QA system, the sub-set of candidate answers as candidate answers to the input natural language question for evaluation and selection of a final answer to the input natural language question.

Abstract: System, structure and method for a conscious, human-like artificial intelligence system in a non-natural entity. The creation of artificial intelligence capable of emulating one or more types of intelligence usually found in humans in a non-natural entity. With the correct structuring and functionality, the Al can think, understand and act as a human would. The Al would be “conscious”. FIG. 1.4 best depicts this.

Abstract: Data points, calendar entries, trends, behavioral patterns may be used to predict and pre-emptively build digital and printable products with selected collections of images without the user's active participation. The collections are selected from files on the user's device, cloud-based photo library, or other libraries shared among other individuals and grouped into thematic products. Based on analysis of the user's collections and on-line behaviors, the system may estimate types and volumes of potential media-centric products, and the resources needed for producing and distributing such media-centric products for a projected period of time. A user interface may take the form of a “virtual curator”, which is a graphical or animated persona for augmenting and managing interactions between the user and the system managing the user's stored media assets. The virtual curator can assume one of many personas, as appropriate, with each user.

Abstract: For correction of an image from an imaging system, a deep-learnt generative model is used as a regularlizer in an inverse solution with a physics model of the degradation behavior of the imaging system. The prior model is based on the generative model, allowing for correction of an image without application specific balancing. The generative model is trained from good images, so difficulty gathering problem-specific training data may be avoided or reduced.

Abstract: This invention relates to an apparatus, system, and method for computing with neuromorphic circuit architectures that have neurons with interconnected internal state information. The interconnected internal state information allows the neurons to enable or strengthen the input to other neurons. Furthermore, neuron internal state information provides insights on the characteristics of the input data that can be used to enhance the performance of the neuromorphic system. The neuromorphic system can be implemented with an artificial phase-change-based neurons.

Abstract: The present invention discloses a system for finding shortest pathways between neurons in a neural network, including a neural space generating module for establishing a three dimensional or higher dimensional neural space database (which may be neuron image database), wherein the three dimensional or higher dimensional neural space database includes a plurality of neurons distributed therein. A neurons connection determining module is used for determined whether there is a connection between each of the plurality of neurons in the three dimensional or higher dimensional neural space database and the others of the plurality of neurons in the three dimensional or higher dimensional neural space database. A neural shortest pathway tables generating module is used for calculating a shortest pathway table of all of a plurality of connected neurons and then stored in a storage device.

Abstract: Methods and systems of predicting the growth rate of hydrogen-induced cracking (HIC) in a physical asset (e.g., a pipeline, storage tank, etc.) are provided. The methodology receives a plurality of inputs regarding physical characteristics of the asset and performs parametric simulations to generate a simulated database of observations of the asset. The database is then used to train, test, and validate one or more expert systems that can then predict the growth rate and other characteristics of the asset over time. The systems herein can also generate alerts as to predicted dangerous conditions and modify inspection schedules based on such growth rate predictions.

Abstract: One or more processors receive hyperspectral band input, biometric input, and cognitive input as response input, from a user sampling a plurality of base foods, each base food prepared with a subset of ingredients and preparation techniques. The response input is transformed to a numeric representation of the respective input. Deep learning techniques are used to train an algorithm using the response data. A probabilistic ranking of base food is generated using unsupervised learning. Probability values of base food, ingredients, and preparation technique, associations preferred by the user, are generated, along with rules which define constraints associated with conditions for base food, ingredient, and preparation techniques, of user preferences. An objective function is generated that includes decision variables respectively aligned with constraints, and in response to optimizing the objective function, a preferred base food and ingredients, with preferred conditions of the user, is determined.

Abstract: A cognitive learning device includes inputs with each including an input path having a transistor device having a storage capacity. A circuit is responsive to the inputs and selects an input set in accordance with a current task, wherein the input set selected modifies a characteristic of the transistor device of one or more corresponding input paths to bias the input set for selection for subsequent accesses.