Abstract: A composite vector is received. A first candidate component vector is generated and evaluated. The first candidate component vector is selected, based on the evaluating, as an accurate component vector. The first candidate component vector is unbundled from the composite vector. The unbundling results in a first reduced vector.

Abstract: The disclosure includes a computer-implemented method of factorizing a vector by utilizing resonator network modules. Such modules include an unbinding module, as well as search-in-superposition modules. The method includes the following steps. A product vector is fed to the unbinding module to obtain unbound vectors. The latter represent estimates of codevectors of the product vector. A first operation is performed on the unbound vectors to obtain quasi-orthogonal vectors. The first operation is reversible. The quasi-orthogonal vectors are fed to the search-in-superposition modules, which rely on a single codebook. In this way, transformed vectors are obtained, utilizing a single codebook. A second operation is performed on the transformed vectors. The second operation is an inverse operation of the first operation, which makes it possible to obtain refined estimates of the codevectors.

Abstract: A computerized neuro-vector-symbolic architecture, that: receives image data associated with an artificial intelligence (AI) task; processes the image data using a frontend that comprises an artificial neural network (ANN) and a vector-symbolic architecture (VSA); and processes an output of the frontend using a backend that comprises a symbolic logical reasoning engine, to solve the AI task. The AI task, for example, may be an abstract visual reasoning task.

Abstract: Embodiments are disclosed for a method. The method includes determining a granularity of hypervectors. The method also includes receiving an input hypervector representing a data structure. Additionally, the method includes performing an iterative process to factorize the input hypervector into individual hypervectors representing the cognitive concepts. The iterative process includes, for each concept: determining an unbound version of a hypervector representing the concept by a blockwise unbinding operation between the input hypervector and estimate hypervectors of other concepts. The iterative process further includes determining a similarity vector indicating a similarity of the unbound version of the hypervector with each candidate code hypervector of the concept. Additionally, the iterative process includes generating an estimate of a hypervector representing the concept by a linear combination of the candidate code hypervectors, and weights of the similarity vector.

Abstract: Embodiments are disclosed for a method. The method includes bundling a set of M code hypervectors, each of dimension D, where M>1. The bundling includes receiving an M-dimensional vector comprising weights for weighting the set of code hypervectors. The bundling further includes mapping the M-dimensional vector to an S-dimensional vector, sk, such that each element of the S-dimensional vector, sk, indicates one of the set of code hypervectors, where S=D/L and L?1. Additionally, the bundling includes building a hypervector such that an ith element of the built hypervector is an ith element of the code hypervector indicated in an ith element of the S-dimensional vector, sk.

Abstract: Predefined concepts are represented by codebooks. Each codebook includes candidate code hypervectors that represent items of a respective concept of the predefined concepts. A neuromorphic memory device with a crossbar array structure includes row lines and column lines stores a value of respective code hypervectors of an codebook. An input hypervector is stored in an input buffer. A plurality of estimate buffers are each associated with a different subset of row lines and a different codebook and initially store estimated hypervectors. An unbound hypervector is computed using the input hypervector and all the estimated hypervectors. An attention vector is computed that indicates a similarity of the unbound hypervector with one estimated hypervector. A linear combination of the one estimated hypervector, weighted by the attention vector, is computed and is stored in the estimate buffer that is associated with the one estimated hypervector.

Abstract: A computer-implemented method for performing a classification of an input signal utilizing a neural network includes: computing, by a feature extraction unit of the neural network, a query vector; and performing, by a classification unit, a factorization of the query vector to a plurality of codebook vectors of a plurality of codebooks to determine a corresponding class of a number of classes. A set of combinations of vector products of the plurality of codebook vectors of the plurality of codebooks establishes a number of classes of the classification unit.

Abstract: A computer-implemented method for performing a classification of an input signal by a neural network includes: computing, by a feature extraction unit of the neural network, a D-dimensional query vector, wherein D is an integer; generating, by a classification unit of the neural network, a set of C fixed D-dimensional quasi-orthogonal bipolar vectors as a fixed classification matrix, wherein C is an integer corresponding to a number of classes of the classification unit; and performing a classification of a query vector based, at least in part, on the fixed classification matrix.

Abstract: A computer-implemented method for factorizing hypervectors in a resonator network includes: receiving an input hypervector representing a data structure; performing an iterative process for each concept in a set of concepts associated with the data structure in order to factorize the input hypervector into a plurality of individual hypervectors representing the set of concepts, wherein the iterative process includes: generating a first estimate of an individual hypervector representing a concept in the set of concepts; generating a similarity vector indicating a similarity of the estimate of the individual hypervector with each candidate attribute hypervector of a plurality of candidate attribute hypervectors representing an attribute associated with the concept; and generating a second estimate of the individual hypervector based, at least in part, on a linear combination of the plurality of candidate attribute hypervectors and performing a non-linear function on the linear combination of the plurality of ca

Abstract: Management systems, methods and mediums are provided for displaying graphics using a programmable symbol animation pre-processor. One method includes identifying a symbol associated with a building graphic, identifying a symbol property to be animated, and determining whether the symbol property is associated with a script. When it is, identifying a plurality of different data points referenced in the script where each data point corresponds to the same device or a respective device in the building. The method identifies a respective value for each identified data point as received from a management system operably connected to each of the plurality of devices, identifies an operation in the script that corresponds to an evaluation of the values of the identified data points, generates a first evaluation result based on the operation, and displays a graphical representation of the symbol based on the first evaluation result and in association with the building graphic.

Abstract: Management systems, methods and mediums are provided. A method includes displaying a building layout graphic, receiving a request to generate a coverage area graphic associated with a monitoring device, generating the coverage area graphic, and displaying the coverage area graphic relative to the building layout graphic. The method also identifies a device having a data point to be monitored by the data processing system, and determines whether the identified device is in the coverage area represented by the coverage area graphic. In response to determining that the identified device is in the coverage area, the method further includes storing a related item identifier associated with the one or more monitoring devices in association with an object corresponding to the identified device. The method receives a selection for the identified device and, in response, displays one or more related item identifiers associated with the one or more monitoring devices.

Abstract: Management systems, methods and mediums are provided for a building automation graphical interface command configuration. One method includes receiving a selection of a graphical element. The method includes receiving a selection of a command control type. The method includes associating the command control type with the graphical element to produce a command control. The method includes receiving at least one property for the command control. At least one property includes at least a parameter name that identifies a target of the command control. The method includes storing the command control. The method includes in response to a user selection or modification of the command control, processing a command to modify the target of the command control.

Abstract: Management systems, methods and mediums are provided for displaying graphics using a programmable symbol animation pre-processor. One method includes identifying a symbol associated with a building graphic, identifying a symbol property to be animated, and determining whether the symbol property is associated with a script. When it is, identifying a plurality of different data points referenced in the script where each data point corresponds to the same device or a respective device in the building. The method identifies a respective value for each identified data point as received from a management system operably connected to each of the plurality of devices, identifies an operation in the script that corresponds to an evaluation of the values of the identified data points, generates a first evaluation result based on the operation, and displays a graphical representation of the symbol based on the first evaluation result and in association with the building graphic.

Abstract: Management systems, methods and mediums are provided. A method includes displaying a building layout graphic, receiving a request to generate a coverage area graphic associated with a monitoring device, generating the coverage area graphic, and displaying the coverage area graphic relative to the building layout graphic. The method also identifies a device having a data point to be monitored by the data processing system, and determines whether the identified device is in the coverage area represented by the coverage area graphic. In response to determining that the identified device is in the coverage area, the method further includes storing a related item identifier associated with the one or more monitoring devices in association with an object corresponding to the identified device. The method receives a selection for the identified device and, in response, displays one or more related item identifiers associated with the one or more monitoring devices.

Abstract: Automation systems, methods, and mediums. A method includes identifying a value for a data point associated with a device in a building. The value is received from a management system operably connected to the device. The method includes mapping the value for the data point to a graphical representation of the value for the data point. The method includes generating a display comprising a graphic for the building and a symbol representing the device. The method includes displaying the graphical representation of the value for the data point in association with the symbol representing the device. Additionally, the method includes modifying the graphical representation of the value based on a change in the value in response to identifying the change in the value from the management system.

Abstract: A method for navigating information includes identifying a value for a property of a first object associated with one or more devices managed by a management system. The method includes displaying a first plurality of tiles for a plurality of objects, including the first object. A first of the tiles is associated with the first object and includes a display of a graphic associated with the object and the identified value for the property. The method includes identifying a plurality of related objects that are related to the first object and displaying a second plurality of tiles for the related objects in response to receiving a selection of the first tile for the first object. Additionally, the method includes displaying, in response to receiving a selection of a second tile in the second plurality of tiles for one of the related objects, information about the one related object.

Abstract: A client manager application for a building management system. A method includes maintaining a client manager application configured to interact with both a web client data processing system and an installed client data processing system to perform building management system functions. The installed client data processing system operates an installed client manager application to provide an installed building management interface. The method includes deploying a browser client manager module to the web client data processing system. A browser building management interface that has substantially the same appearance and functionality as the installed building management interface. The server interacts with both the installed client data processing system and the web client data processing system to perform the building management system functions. The client manager application can be configured to run in a web client data processing system as well as in an installed client data processing system.

Abstract: Management systems, methods, and mediums. A method includes identifying a set of layers and a zoom factor based on a depth of a graphic to be displayed. The set of layers comprise symbols for objects corresponding to devices in a building managed by the management system. The method includes identifying a number of visible objects from the objects of the symbols in the identified set of layers based on the zoom factor. The method includes identifying a state of a device represented by a visual object in the number of visible objects from the management system communicably coupled with the devices. Additionally, the method includes generating a display for the depth. The display includes the identified set of layers, a symbol for each of the number of visible objects in the identified set of layers, and a graphical indication of the state of the device.

Abstract: A method for navigating information includes identifying a value for a property of a first object associated with one or more devices managed by a management system. The method includes displaying a first plurality of tiles for a plurality of objects, including the first object. A first of the tiles is associated with the first object and includes a display of a graphic associated with the object and the identified value for the property. The method includes identifying a plurality of related objects that are related to the first object and displaying a second plurality of tiles for the related objects in response to receiving a selection of the first tile for the first object. Additionally, the method includes displaying, in response to receiving a selection of a second tile in the second plurality of tiles for one of the related objects, information about the one related object.

Abstract: Management systems, methods, and mediums. A method includes identifying a set of layers and a zoom factor based on a depth of a graphic to be displayed. The set of layers comprise symbols for objects corresponding to devices in a building managed by the management system. The method includes identifying a number of visible objects from the objects of the symbols in the identified set of layers based on the zoom factor. The method includes identifying a state of a device represented by a visual object in the number of visible objects from the management system communicably coupled with the devices. Additionally, the method includes generating a display for the depth. The display includes the identified set of layers, a symbol for each of the number of visible objects in the identified set of layers, and a graphical indication of the state of the device.