Abstract: The present disclosure provides a method and device for intelligent control of heating furnace combustion based on a big data cloud platform, which relates to the technical field of artificial intelligence control. The method includes: construction of big data cloud platform based on production and operation parameters of the heating furnace; identification of key factors in the production process of the heating furnace by using big data mining technology; independent deployment of traditional heating furnace combustion control systems based on the mechanism model; and integration of cloud platform big data expert knowledge base and the heating furnace combustion intelligent control system.

Abstract: Disclosed is a dynamic wall heat exchange device based on piezoelectric excitation, comprising a base support. A sidewall of the base support is provided with a strip-shaped opening, and a low-temperature heat source runner is arranged in the strip-shaped opening. The base support is further provided with a high-temperature heat source runner. The high-temperature heat source runner comprises a main pipe erected on the base support. The main pipe is sleeved with a heat exchange sleeve, and corrugated pipes are connected to the main pipe in series. The low-temperature heat source runner also penetrates through the heat exchange sleeve. The base support is provided with a plurality of elastic cantilever arms, the lower ends of each of the elastic cantilever arms is provided with an inertial mass block, and a piezoelectric stack is arranged between the elastic cantilever arm and the inertial mass block.

Abstract: A robot having four screw propeller barrels and able to walk on all types of terrains is provided and includes: a housing, wherein each of four corners of the housing is arranged with a driving shaft, four driving shafts are arranged for the four corners and form a rectangle and are connected to a motor, a rotation surface of the driving shaft is parallel to a same vertical surface. An end of the driving shaft is arranged with a connection base, the connection base is arranged with a shaftless motor, an output end of the shaftless motor has a rotation surface perpendicular to the rotation surface of the driving shaft. The output end of the shaftless motor is arranged with a connection bracket, a bottom surface of the connection bracket is arranged with a plurality of connection rings arranged successively along a straight line.

Abstract: The disclosed embodiments provide a system for performing online hyperparameter tuning in distributed machine learning. During operation, the system uses input data for a first set of versions of a statistical model for a set of entities to calculate a batch of performance metrics for the first set of versions. Next, the system applies an optimization technique to the batch to produce updates to a set of hyperparameters for the statistical model. The system then uses the updates to modulate the execution of a second set of versions of the statistical model for the set of entities. When a new entity is added to the set of entities, the system updates the set of hyperparameters with a new dimension for the new entity.

Abstract: One embodiment of the present invention sets forth a technique for managing machine learning. The technique includes organizing a set of reusable components for performing machine learning under a framework. The technique also includes representing, within the framework, a machine learning model as a graph-based structure that includes nodes representing a subset of the reusable components and edges representing input-output relationships between pairs of the nodes. The technique further includes validating the machine learning model based on inputs and outputs associated with the nodes and the input-output relationships represented by the edges in the graph-based structure. Finally, the technique includes generating the machine learning model according to the graph-based structure and configurations for the subset of the reusable components.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains a hierarchical representation containing a set of namespaces of a set of features shared by a set of statistical models. Next, the system uses the hierarchical representation to obtain, from one or more execution environments, a subset of the features for use in calculating the derived feature. The system then applies a formula from the hierarchical representation to the subset of the features to produce the derived feature. Finally, the system provides the derived feature for use by one or more of the statistical models.

Abstract: The disclosed embodiments provide a method and system for performing regularized model adaptation for in-session recommendations. During operation, the system obtains, from a server, a first global version of a statistical model. During a first user session with a user, the system improves a performance of the statistical model by using the first global version to output one or more recommendations to the user and using the first global version and user feedback from the user to create a first personalized version of the statistical model. At an end of the first user session, the system transmits an update containing a difference between the first personalized version and the first global version to the server for use in producing a second global version of the statistical model by the server.

Abstract: One embodiment of the present invention sets forth a technique for processing training data for a machine learning model. The technique includes training the machine learning model using training data comprising a set of features and a set of original labels associated with the set of features. The technique also includes generating multiple groupings of the training data based on internal representations of the training data in the machine learning model. The technique further includes replacing, in a first subset of groupings of the training data, a first subset of the original labels with updated labels based at least on occurrences of values for the original labels in the first subset of groupings.

Abstract: A system and method for managing asynchronously receiving updates and merging updates into global versions of a statistical model using version control are disclosed. During operation, the system transmits a first global version of a statistical model to a set of client computer systems. Next, the system obtains, from a first subset of the client computer systems, a first set of updates to the first global version. The system then merges the first set of updates into a second global version of the statistical model. Finally, the system transmits the second global version to the client computer systems asynchronously from receiving a second set of updates to the first and/or second global versions from a second subset of the client computer systems.

Abstract: The disclosed embodiments provide a system for performing online hyperparameter tuning in distributed machine learning. During operation, the system uses input data for a first set of versions of a statistical model for a set of entities to calculate a batch of performance metrics for the first set of versions. Next, the system applies an optimization technique to the batch to produce updates to a set of hyperparameters for the statistical model. The system then uses the updates to modulate the execution of a second set of versions of the statistical model for the set of entities. When a new entity is added to the set of entities, the system updates the set of hyperparameters with a new dimension for the new entity.

Abstract: Examples are disclosed herein that relate to gaze tracking. One example provides a computing device including an eye-tracking system including an image sensor, a logic device, and a storage device comprising instructions executable by the logic device to track an eye gaze direction by acquiring an image of the eye via the eye-tracking system, and determining a determined location of a center of a lens of the eye from the image of the eye. The instructions are further executable to adjust the determined location of the center of the lens on a sub-pixel scale by applying a predetermined sub-pixel offset to the determined location of the center of the lens to produce an adjusted location of the center of the lens, to determine a gaze direction from the adjusted location of the center of the lens, and perform an action on a computing device based on the gaze direction.

Abstract: Examples are disclosed herein that are related to gaze tracking via image data. One example provides, on a gaze tracking system comprising an image sensor, a method of determining a gaze direction, the method comprising acquiring image data via the image sensor, detecting in the image data facial features of a human subject, determining an eye rotation center based upon the facial features using a calibrated face model, determining an estimated position of a center of a lens of an eye from the image data, determining an optical axis based upon the eye rotation center and the estimated position of the center of the lens, determining a visual axis by applying an adjustment to the optical axis, determining the gaze direction based upon the visual axis, and providing an output based upon the gaze direction.

Abstract: Learning to rank modeling in the context of an on-line social network is described. A learning to rank model can learn from pairwise preference (e.g., job posting A is more relevant than job posting B for a particular member profile) thus directly optimizing for the rank order of job postings for each member profile. With ranking position taken into consideration during training, top-ranked job postings may be treated by a recommendation system as being of more importance than lower-ranked job postings. In addition, a learning to rank approach may also result in an equal optimization across all member profiles and help minimize bias towards those member profiles that have been paired with a larger number of job postings.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains a hierarchical representation containing a set of namespaces of a set of features shared by a set of statistical models. Next, the system uses the hierarchical representation to obtain, from one or more execution environments, a subset of the features for use in calculating the derived feature. The system then applies a formula from the hierarchical representation to the subset of the features to produce the derived feature. Finally, the system provides the derived feature for use by one or more of the statistical models.

Abstract: Learning to rank modeling in the context of an on-line social network is described. A learning to rank model can learn from pairwise preference (e.g., job posting A is more relevant than job posting B for a particular member profile) thus directly optimizing for the rank order of job postings for each member profile. With ranking position taken into consideration during training, top-ranked job postings may be treated by a recommendation system as being of more importance than lower-ranked job postings. In addition, a learning to rank approach may also result in an equal optimization across all member profiles and help minimize bias towards those member profiles that have been paired with a larger number of job postings.

Abstract: The disclosed embodiments provide a system and method for performing version control for asynchronous distributed machine learning. During operation, the system transmits a first global version of a statistical model to a set of client computer systems. Next, the system obtains, from a first subset of the client computer systems, a first set of updates to the first global version. The system then merges the first set of updates into a second global version of the statistical model. Finally, the system transmits the second global version to the client computer systems asynchronously from receiving a second set of updates to the first and/or second global versions from a second subset of the client computer systems.

Abstract: The disclosed embodiments provide a method and system for performing regularized model adaptation for in-session recommendations. During operation, the system obtains, from a server, a first global version of a statistical model. During a first user session with a user, the system improves a performance of the statistical model by using the first global version to output one or more recommendations to the user and using the first global version and user feedback from the user to create a first personalized version of the statistical model. At an end of the first user session, the system transmits an update containing a difference between the first personalized version and the first global version to the server for use in producing a second global version of the statistical model by the server.

Abstract: Nonlinear featurization of decision trees for linear regression modeling in the context of an on-line social network is described. A computer-implemented converter is provided that is capable of reading a decision tree structure that is included in the learning to rank algorithm and convert each path from root to a leaf into an s-expression. The s-expressions are used as additional features to train a logistic regression model.

Abstract: Learning to rank modeling in the context of an on-line social network is described. A learning to rank model can learn from pairwise preference (e.g., job posting A is more relevant than job posting B for a particular member profile) thus directly optimizing for the rank order of job postings for each member profile. With ranking position taken into consideration during training, top-ranked job postings may be treated by a recommendation system as being of more importance than lower-ranked job postings. In addition, a learning to rank approach may also result in an equal optimization across all member profiles and help minimize bias towards those member profiles that have been paired with a larger number of job postings.

Abstract: Methods, compositions, and systems for detecting gamma radiation is disclosed and described. A compound for detecting gamma radiation can comprise a conjugated imidazole having the following structure: [Formula I] where at least one of R1, R2, and R3 are conjugated organic groups. Additionally, the conjugated imidazole can be capable of reacting with a radical or ion formed by the reaction of gamma radiation with a radical generating component such as a halogen solvent to decrease a molar extinction coefficient of the conjugated imidazole in the visible light region or to quench fluorescence of the conjugated imidazole. As a sensor (100), a radiation detection indicator (108) can indicate the change in molar extinction coefficient or fluorescence of the conjugated imidazole material (120) upon exposure to gamma radiation.