Abstract: Implementations are directed to processing a content object model through a ML model to provide a set of base content feature representations, processing a style object model through the ML model to provide sets of base style feature representations, executing iterations including: generating, by the ML model, sets of stylized feature representations for an initial stylized object model, the initial stylized object model having one or more adjusted parameters relative to a previous iteration, determining a total loss based on the sets of stylized feature representations, the set of base content feature representations, and the sets of base style feature representations, and determining that the total loss is non-optimized, and in response, initiating a next iteration, executing an iteration of the iterative process, the iteration including determining that the total loss is optimized, and in response providing the initial stylized object model as output of the iterative process.

Abstract: In some implementations, a robot host may receive a video associated with assembly using a plurality of sub-objects. The robot host may determine spatio-temporal features based on the video and may identify a plurality of actions represented in the video based on the spatio-temporal features. The robot host may map the plurality of actions to the plurality of sub-objects to generate an assembly plan and may combine output from a point cloud model and output from a color embedding model to generate a plurality of sets of coordinates corresponding to the plurality of sub-objects. The robot host may perform object segmentation to estimate a plurality of grip points and a plurality of widths corresponding to the plurality of sub-objects. Accordingly, the robot host may generate instructions, for robotic machines, based on the assembly plan, the plurality of sets of coordinates, the plurality of grip points, and the plurality of widths.

Abstract: Methods, systems, and computer-readable storage media for receiving, by an aromatic simulation platform, a recipe including descriptions indicative of ingredients of a consumable, processing the recipe through a first neural network to provide a recipe embedding, processing an ingredients profile to determine an aroma compounds profile representing the ingredients of the ingredients profile, processing the aroma compounds profile through a second neural network to provide an aroma embedding, and processing the recipe embedding and the aroma embedding through a third neural network to provide an aroma profile representative of the consumable of the recipe.

Abstract: In some examples, generative network-based floor plan generation may include receiving, for a floor plan that is to be classified, a layout graph for which user constraints are encoded as a plurality of room types. The user constraints may include spatial connections therebetween. Based on the layout graph, embedding vectors for each room type of the plurality of room types may be generated. Bounding boxes and segmentation masks may be determined for each room embedding from the layout graph, and based on an analysis of the embedding vectors. A space layout may be generated by combining the bounding boxes and the segmentation masks. The floor plan may be generated based on an analysis of the space layout, and synthesized based on the space layout, noise, and a contextual graph embedding to generate a synthesized floor plan. The synthesized floor plan may be classified as authentic or not-authentic.

Abstract: In some examples, stylization-based floor plan generation may include receiving, for a floor plan that is to be generated, a layout graph for which user constraints are encoded as a plurality of room types. The user constraints may include spatial connections therebetween. Based on the layout graph, embedding vectors may be generated for each room type of the plurality of room types. Bounding boxes and segmentation masks may be determined for each room embedding from the layout graph, and based on an analysis of the embedding vectors for each room type of the plurality of room types. A space layout may be generated by combining the bounding boxes and the segmentation masks. A floor plan may be generated based on an analysis of the space layout and an input boundary feature map.

Abstract: Implementations are directed to receiving a target object model representative of a target object, receiving a source object model representative of a source object, defining a set of target segments and a set of source segments using a segmentation machine learning (ML) model, for each target segment and source segment pair in a set of target segment and source segment pairs, generating a compatibility score representing a degree of similarity between a target segment and a source segment, the compatibility score calculated based on global feature representations of each of the target segment and the source segment, each global feature representation determined from a ML model, selecting a source segment for style transfer based on compatibility scores, and merging the source segment into the target object model to replace a respective target segment within the target object model and providing a stylized target object model.

Abstract: Methods, systems, and computer-readable storage media for receiving, by an aromatic simulation platform, a recipe including descriptions indicative of ingredients of a consumable, processing the recipe through a first neural network to provide a recipe embedding, processing an ingredients profile to determine an aroma compounds profile representing the ingredients of the ingredients profile, processing the aroma compounds profile through a second neural network to provide an aroma embedding, and processing the recipe embedding and the aroma embedding through a third neural network to provide an aroma profile representative of the consumable of the recipe.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support mechanisms for generating a feasible assembly plan for a product based on data analytics. In aspects, information on components of a product is obtained from one or more product models (e.g., a three-dimensional (3D) computer aided design (CAD) model) that define the individual components of the product. The individual component information may be used to represent the assembly of the product as an assembly graph, in which each node of the assembly graph represents one of the components of the product to be assembled. The assembly graph is passed through a set of data analytics modules to generate the feasible assembly plan, or assembly sequence, as a series of sequential contact predictions, wherein each contact prediction identifies a component to be connected to one or more other components of the product.

Abstract: An interactive troubleshooting assistant and method for troubleshooting a system in real time to repair (fix) one or more problems in a system is disclosed. The interactive troubleshooting assistant and method may include receiving multimodal inputs from sensors, wearable devices, a person, etc. that may be input into a feature extractor including attention layers and pre-processing units of a cloud computing system hosted by one or more servers, such as a private cloud system. A pre-processing unit converts the raw multimodal input into a structed form so that an attention layer can give weights to features provided by the pre-processing unit according to their importance. The weighted extracted features may be provided to an actions predictor. The actions predictor generates the most suitable action based on the weighted extracted features generated by the feature extractor based on the multimodal inputs.

Abstract: The disclosed system and method provide a way to create, update, and execute dynamic goal plans. Updating a dynamic goal plan may be based on the initial sequence of actions of the goal plan as well as the corresponding states of the actions. By using a sequence to sequence model, a goal plan can still be processed when the length of the input (initial sequence of actions) differs from the length of the output (updated sequence of actions). A sequence to sequence model can determine the interdependencies between actions that can contribute to the optimal order in which actions can efficiently be performed. A single layer neural network or clustering can be used to approximate the state of a goal plan that may be capable infinite states. This approximation improves accuracy in capturing the state of a goal plan, thereby improving accuracy in predicting the future state of a system, which can help with planning (e.g., gathering resources in advance).

Abstract: The present disclosure relates to a system, and method for computer-based recursive learning of artificial intelligence (AI) apprentice agents. The system includes a system circuitry in communication with a database and a memory. The system circuitry is configured to receive a new data-structure comprising one or more inputs and a goal, and convert, using a perception agent, the one or more inputs of the new data-structure into one or more input feature parameters of the new data-structure. The system circuitry is configured to obtain, using a reasoning agent, an action for the new data-structure, and determine, using an evaluation agent, whether the action for the new data-structure generates the goal of the new data-structure. When it is determined that the action generates the goal of the new data-structure, the system circuitry is further configured to store the new data-structure in the database.

Abstract: Implementations are directed to processing a content object model through a ML model to provide a set of base content feature representations, processing a style object model through the ML model to provide a set of base style feature representations, executing iterations including: generating, by the ML model, a set of stylized feature representations for an initial stylized object model, the initial stylized object model having one or more adjusted parameters relative to a previous iteration, determining a total loss based on the set of stylized feature representations, the set of base content feature representations, and the sets of base style feature representations, and determining that the total loss is non-optimized, and in response, initiating a next iteration, executing an iteration including determining that the total loss is optimized, and in response providing the initial stylized object model as output of the iterative process.

Abstract: Implementations are directed to processing a content object model through a ML model to provide a set of base content feature representations, processing a style object model through the ML model to provide sets of base style feature representations, executing iterations including: generating, by the ML model, sets of stylized feature representations for an initial stylized object model, the initial stylized object model having one or more adjusted parameters relative to a previous iteration, determining a total loss based on the sets of stylized feature representations, the set of base content feature representations, and the sets of base style feature representations, and determining that the total loss is non-optimized, and in response, initiating a next iteration, executing an iteration of the iterative process, the iteration including determining that the total loss is optimized, and in response providing the initial stylized object model as output of the iterative process.

Abstract: Examples of article designing are described herein. In an example, image data, margin data, and sales data corresponding to a plurality of articles may be obtained. The obtained data may be analyzed to identify a first article image of a first article and a second article image of a second article. The first article image is integrated with the second article image, based on an article attribute to generate a transformed article image. The article attribute may be an attribute having a maximum likelihood of making the article popular. The transformed article image may be filtered based on predefined filtering rules to obtain a curated article design image. The curated article design image is assessed to generate a design score indicative of a popularity and/or a sellability of an article, and a design of the article may be selected for a post design selection process, based on the design score.

Abstract: Implementations of the present disclosure include generating, by a design generation assistant, a design image representing a design subject, the design subject having one or more regulations applicable thereto, querying, by a regulation assistant, an answer extractor to provide a query result based on a query, the answer extractor including at least one deep learning model that processes the query to provide the query result, the query being descriptive of at least a portion of the design subject, the query result being representative of at least one regulation applicable to the design subject, and displaying, within a graphical user interface (GUI), the query result.

Abstract: In some examples, artificial intelligence-based intelligent programming assistance may include ascertaining, for a software program that is to be completed, code for the program, and identifying, based on an analysis of error message-based contextual information associated with the ascertained code, an error in the ascertained code. A resolution to the identified error may be generated, and the code may be modified to resolve the identified error, Based on an analysis of problem description-based contextual information associated with the ascertained code, a next token associated with the ascertained code may be generated, and used to generate further code for the program. A performance of a user may be analyzed with respect to generation of the code for the program to generate feedback for the user. A query associated with the program may be ascertained from the user, and classified by utilizing an ontology to generate a response to the query.

Abstract: A call center system for reducing communication latency includes an input/output (I/O) interface for receiving one or more queries from a customer terminal; a processor in communication with the I/O interface; and non-transitory computer readable media in communication with the processor that stores instruction code. The instruction code is executed by the processor and causes the processor to route the one or more queries to a plurality of artificial intelligent (AI) logic modules and receive, from one or more of the AI logic modules, information that facilitates providing, by a call center agent, responses to the one or more queries. The processor also routes actual responses to the one or more queries made by the call center agent to the AI logic modules; and receives from at least one AI logic module one or more scores associated with one or more metrics that rate different aspects if the actual responses.

Abstract: A crowdsource assistant provides guidance to crowdsource resources navigating a crowdsource platform to bid for and be accepted to accomplish tasks. The crowdsource assistant utilizes machine learning to train similarity computation models that improve the crowdsource assistant's computing capability to generate more relevant recommendations to a resource in a faster and more efficient manner.

Abstract: The disclosed system and method provide a way to create, update, and execute dynamic goal plans. Updating a dynamic goal plan may be based on the initial sequence of actions of the goal plan as well as the corresponding states of the actions. By using a sequence to sequence model, a goal plan can still be processed when the length of the input (initial sequence of actions) differs from the length of the output (updated sequence of actions). A sequence to sequence model can determine the interdependencies between actions that can contribute to the optimal order in which actions can efficiently be performed. A single layer neural network or clustering can be used to approximate the state of a goal plan that may be capable infinite states. This approximation improves accuracy in capturing the state of a goal plan, thereby improving accuracy in predicting the future state of a system, which can help with planning (e.g., gathering resources in advance).

Abstract: Implementations are directed to receiving a target object model representative of a target object, receiving a source object model representative of a source object, defining a set of target segments and a set of source segments using a segmentation machine learning (ML) model, for each target segment and source segment pair in a set of target segment and source segment pairs, generating a compatibility score representing a degree of similarity between a target segment and a source segment, the compatibility score calculated based on global feature representations of each of the target segment and the source segment, each global feature representation determined from a ML model, selecting a source segment for style transfer based on compatibility scores, and merging the source segment into the target object model to replace a respective target segment within the target object model and providing a stylized target object model.