Abstract: Machine learning version management method for a prediction service includes receiving a prediction request, determining application metadata for the request that defines routing logic and a machine learning framework version, determining model metadata for the request that defines at least one model and at least one model version, forwarding the prediction request to the at least one model with the at least one model version, and returning a prediction from the at least one model to a requestor.

Abstract: Methods and systems for machine learning inferencing based on directed acyclic graphs are presented. A request for a machine learning application is received from a tenant application. A tenant identifier that identifies one of the tenants is determined from the request. Based on the tenant identifier and a type of the machine learning application, configuration parameters and a graph structure are determined. The graph structure defines a flow of operations for the machine learning application. Nodes of the graph structure are executed based on the configuration parameters to obtain a scoring result. Execution of a node causes a machine learning model generated for the first tenant to be applied to data related to the request. The scoring result is returned in response to the request.

Abstract: Methods and systems for multi-model scoring in a multi-tenant system are presented. A request for a machine learning application is received from a tenant application. A tenant identifier that identifies one of the multiple tenants is determined. Based on the tenant identifier and a type of the machine learning application, a first and a second machine learning models are determined. The first machine learning model was generated based on a first training data set associated with the tenant identifier. The second machine learning model that was generated based on a second training data set associated with the tenant identifier. A flow of operations that includes running the first and second machine learning models with data related to the request is executed to obtain a scoring result. The scoring result is returned to the tenant application in response to the request.

Abstract: A method by one or more electronic devices for spinning up a scoring container on demand. The method includes receiving, from an orchestrator component via an application programming interface (API), a request to spin up the scoring container, wherein the scoring container is configured to provide scoring functionality, spinning up the scoring container responsive to receiving the request to spin up the scoring container, and providing, to the orchestrator component via the API, a response to the request to spin up the scoring container, wherein the response includes a uniform resource locator (URL) to use to submit scoring requests to the scoring container.

Abstract: A method performs service discovery in a machine learning service. The method includes detecting initialization of at least one service container, identifying label information in the at least one service container, collecting the label information for the initializing at least one service container, and storing the label information in a routing information storage to enable routing of requests to the at least one service container.

Abstract: A method of a base scorer in a scoring service container includes sending a model identifier to a model loader of an application specific scorer in the scoring service container, receiving a model object from the model loader in response to sending the model identifier, sending a request for a scoring from a client application to a scoring function of the application specific scorer, receiving the scoring from the application specific scorer, and returning the scoring to the client application.

Abstract: A method by one or more electronic devices to provision an infrastructure for a machine learning application in a multi-tenant on-demand serving infrastructure. The method includes storing a plurality of templates, wherein each of the plurality of templates indicates a scoring interface, a web server, a definition of a continuous integration pipeline, and a definition of a continuous deployment pipeline, receiving a request to provision the infrastructure for the machine learning application using a specified template from the plurality of templates, and provisioning the infrastructure for the machine learning application using the specified template to create a version control system repository, a continuous integration pipeline, and a continuous deployment pipeline.

Abstract: A method by a router component in a multi-tenant on-demand serving infrastructure to route scoring requests to scoring containers. The method includes receiving a scoring request, determining a machine learning application associated with the scoring request, determining whether a router instance for the machine learning application exists, and responsive to a determination that a router instance for the machine learning application does not exist, obtaining a configuration object for the machine learning application and instantiating the router instance for the machine learning application based on the configuration object for the machine learning application. The method further includes invoking the router instance for the machine learning application to route the scoring request associated with the machine learning application to a scoring container that provides scoring functionality for the machine learning application.

Abstract: A machine learning serving infrastructure implementing a method of receiving or detecting an update of container metrics including resource usage and serviced requests per model or per container, processing the container metrics per model or per container to determine recent resource usage and serviced requests per model or per container, and rebalancing distribution of models to a plurality of containers to decrease a detected load imbalance between containers or a stressed container in the plurality of containers.

Abstract: Machine learning version management method for a prediction service includes receiving a prediction request, determining application metadata for the request that defines routing logic and a machine learning framework version, determining model metadata for the request that defines at least one model and at least one model version, forwarding the prediction request to the at least one model with the at least one model version, and returning a prediction from the at least one model to a requestor.

Abstract: Using container information to select containers for executing models is described. A system receives a request from an application and identifies a version of a machine-learning model associated with the request. The system identifies a set of each serving container corresponding to the machine-learning model from a cluster of available serving containers associated with the version of the machine-learning model. The system selects a serving container from the set of each serving container corresponding to the machine-learning model. If the machine-learning model is not loaded in the serving container, the system loads the machine-learning model in the serving container. If the machine-learning model is loaded in the serving container, the system executes, in the serving container, the machine-learning model on behalf of the request. The system responds to the request based on executing the machine-learning model on behalf of the request.

Abstract: Using container and model information to select containers for executing models is described. A system receives a request from an application and identifies a version of a machine-learning model associated with the request. The system identifies model information associated with machine learning models corresponding to a cluster of available serving containers associated with the version of the machine-learning model. The system uses the model information to select a serving container from the cluster of available serving containers. If the machine-learning model is not loaded in the serving container, the system loads the machine-learning model in the serving container. If the machine-learning model is loaded in the serving container, the system executes, in the serving container, the machine-learning model on behalf of the request. The system responds to the request based on executing the machine-learning model on behalf of the request.

Abstract: The invention can be defined in its most general form as a device for sheet material corrugation by means of bending and can be applied in the devices for production of single curvature folded core used in production of aircraft and craft curvilinear panels. The invention has for its object to broaden the technological capabilities. For that the mandrel is made in the form of a set of alternating rows of plane elements (4, 6, 7) made in the form of trapeziums (4) and isosceles triangles (6, 7) fixed on the flexible material of the base (5) forming thus the gap-pivots between the elements. At the same time the bases of the triangular elements (6, 7) face each other in pairs along the bending lines while said bending lines correspond to the protrusions lines of the core folded structure. The base of the triangular elements (6, 7) is the function of the folded core block curvature radius and the geometrical parameters of the zigzag crimp structure.

Abstract: The invention can be defined in its most general form as a technology for production of corrugated structures from foliated composite materials and can be used for production of sandwich panels used in aircraft construction, shipbuilding, and in building units.

Abstract: The invention can be defined in its most general form as a building unit, namely the sandwich panel with light core from corrugated sheet material in the form of zigzag crimp, and can be used in aircraft construction, as well as in shipbuilding and construction. Making use of the claimed invention will improve the weight efficiency, the strength and the manufacturability of the panel. The beneficial effect is attained due to the fact that the plane slanting ridges are connected along the protrusion and recess zigzag lines by means of curvilinear parts, whose radius is not less than the core material thickness, whereby along said parts is a line perforation enabling the adhesive material to get into the holes of the perforation in the course of core-skins assembling.

Abstract: The invention can be defined in its most general form as a method for production of sandwich panels with zigzag corrugated core (2) from sheet material used in aircraft construction, shipbuilding, and other branches of industry. With the aim to improve the quality and ease of sheet blank folding into the 3-D relief structure in the sheet blank at locations of crimp zigzag lines (4) protrusions and recesses the holes are punched with the diameter not less than the sheet blank bending radius.

Abstract: The invention can be defined in its most general form as a device for sheet material corrugation by means of bending and can be used in production of light core for sandwich panels, and elements of heat-exchange apparatus. The device includes the pivotedly connected in-between shaping and auxiliary systems of dies (4) and the drive for their transformation including the system of vacuumization and the chamber (3) made of flexible gas-proof material where the latter of said systems is fixed. Used to set the system of shaping dies (4) into its initial plane state is the mechanism made in the form of rigid chamber with the perforated cap (2) providing the possibility to connect the chamber to the system of vacuumization. The device also includes the subsidiary flexible removable vacuum chamber (8) wherein the blank (6) from sheet material is placed in contact with the shaping system of dies (4).

Abstract: The device contains the transformable mandrel (12) made of plane elements (14) pivotedly connected in-between with the use of gas-proof fabric (15,16), the means for preliminary and final mandrel transformation including the flexible vacuum chamber and traverse-pusher (11) with the drive (10), and the mechanism for putting the transformable mandrel into its initial plane state made in the form of two parallel slabs (6, 7) with the drive for their reciprocal travel (9). The means for preliminary mandrel transformation is made in the form of the system of pushers placed in rows on the lower and the upper slabs with individual drives. The perforations in the slabs provide the possibility for the pushers to interact with the transformable mandrel placed between the slabs whereas the mandrel with sheet blank article is put into the vacuum chamber.

Abstract: The invention can be defined in its most general form as a 3-D light core from sheet material, especially from “NOMEX” polymeric paper, and can be used in production of sandwich panels as applied in aircraft production, construction and other branches of industry. With the aim to improve the core mechanical and unit weight properties, the paper base is perforated thereby increasing the base-binder bonding strength, whereof the binder is applied onto both sides of the base to increase its structure rigidity, owing to bonding of binder layers in-between at the locations of the holes. The quantity of the holes and their diameter are defined in a formula.

Abstract: The invention can be defined in its most general form as the method for sheet material corrugation and can be used for production of aircraft curvilinear sandwich panel folded structure light corrugated core. With the aim to broaden the technological capabilities the corrugated blank is compressed from its sides to joining of ridges providing in its lateral section the curvature radius defined by the curvilinear folded structure design parameters and fixed in such condition block is thermally treated for inner stresses relief in the article material whereupon it is stretched to the curvilinear folded structure parameters given.