Abstract: Various systems and methods for modeling a manufacturing assembly line are disclosed herein. Some embodiments relate to operating a processor to receive cell data and line production data, determine one or more production associations between the cell data and the line production data; evaluate the one or more production associations to identify one or more critical production associations; retrieve the cell data and the line production data associated with the one or more critical production associations; and train a predictive model with the retrieved cell data and the retrieved line production data to predict the production level of the manufacturing assembly line.

Abstract: A computer-implemented method, medium, and system are disclosed. One example computer-implemented method performed by a server includes obtaining training task information from a task party. The training task information includes information about a to-be-pretrained model and information about a to-be-trained target model. A respective task acceptance indication from each of at least one of a plurality of data parties is received to obtain a candidate data party set. The information about the to-be-pretrained model is sent to each data party in the candidate data party set. A respective pre-trained model of each data party is received. A respective performance parameter of the respective pre-trained model of each data party is obtained. One or more target data parties from the candidate data party set is determined. The information about the to-be-trained target model is sent to the one or more target data parties to obtain a target model.

Abstract: Some embodiments include a process, including obtaining, with a classical computer system, a mathematical problem to be solved by a quantum computing system, wherein: the quantum computing system comprises one or more quantum computers, the mathematical problem involves more variables than any of the one or more quantum computers have logical qubits, and solving the mathematical problem entails determining values of the variables; decomposing, with the classical computer system, the mathematical problem into a plurality of sub-problems, wherein decomposing the mathematical problem into the plurality of sub-problems comprises decomposing the mathematical problem with machine learning into quantum circuits; causing, with the classical computer system, the quantum computing system to solve each of the sub-problems and aggregate solutions to the sub-problems to determine a solution to the mathematical problem; and storing, with the classical computer system, the solution to the mathematical problem in memory.

Abstract: Techniques for massively-parallel real-time database-integrated machine learning (ML) inference are described. An ML model is deployed as one or more model serving units behind an endpoint. The ML model can be associated with a virtual table or function, and a query that is received that references the virtual table or function can be processed by issuing inference requests to the endpoint by the query execution engine(s).

Abstract: Techniques for model adaptation are described. For example, a method of receiving a call to provide either a model variant or a model variant profile of a deep learning model, the call including desired performance of the deep learning model, a deep learning model identifier, and current edge device characteristics; comparing the received current edge device characteristics to available model variants and profiles based on the desired performance of the deep learning model to generate or select a model variant or profile, the available model variants and profiles determined by the model identifier; and sending the generated or selected model variant or profile to the edge device to use in inference is detailed.

Abstract: A system and method for utilizing a logical graphical model for data analysis are described. The system provides a “PGM authoring tool” that enables a user to employ a logical graphical model to create, edit, and browse the assertions and inferences in a probabilistic graphical model.

Abstract: A compiler receives a description of a machine learning network and generates a computer program that implements the machine learning network. The computer program includes statically scheduled instructions that are executed by a mesh of processing elements (Tiles). The instructions executed by the Tiles are statically scheduled because the compiler can determine which instructions are executed by which Tiles at what times. For example, for the statically scheduled instructions, there are no conditions, branching or data dependencies that can be resolved only at run-time, and which would affect the timing and order of the execution of the instructions.

Abstract: A computer-implemented method that includes receiving, by a processing unit, an instruction that specifies data values for performing a tensor computation. In response to receiving the instruction, the method may include, performing, by the processing unit, the tensor computation by executing a loop nest comprising a plurality of loops, wherein a structure of the loop nest is defined based on one or more of the data values of the instruction. The tensor computation can be at least a portion of a computation of a neural network layer. The data values specified by the instruction may comprise a value that specifies a type of the neural network layer, and the structure of the loop nest can be defined at least in part by the type of the neural network layer.

Abstract: A data processing method includes: obtaining first sample data, and determining a target model and a feature set corresponding to the target model; obtaining second sample data, and dividing the second sample data into a development data set and a validation data set based on a predetermined proportion or a predetermined chronological order; respectively determining final sample data of the first sample data and retained sample data of the development data set based on the target model, the feature set corresponding to the target model, the first sample data, the development data set and the validation data set; and merging the final sample data and the retained sample data to obtain a modeling data set corresponding to a first business project. A data processing apparatus, and a computer device for implementing the data processing method are further provided.

Abstract: A method for standardized model interaction can include: determining a model composition, receiving an input, converting the input into a standard object, converting the standard input object into a model-specific input (MSI) object, executing the model using the MSI object, converting the output from the model-specific output (MSO) object to a standard object, repeating previous steps for each successive model within the model composition, and providing a final model output.

Abstract: The techniques herein include using an input context to determine a suggested action. One or more explanations may also be determined and returned along with the suggested action. The one or more explanations may include (i) one or more most similar cases to the suggested case (e.g., the case associated with the suggested action) and, optionally, a conviction score for each nearby cases; (ii) action probabilities, (iii) excluding cases and distances, (iv) archetype and/or counterfactual cases for the suggested action; (v) feature residuals; (vi) regional model complexity; (vii) fractional dimensionality; (viii) prediction conviction; (ix) feature prediction contribution; and/or other measures such as the ones discussed herein, including certainty. In some embodiments, the explanation data may be used to determine whether to perform a suggested action.

Abstract: The techniques herein include using an input context to determine a suggested action. One or more explanations may also be determined and returned along with the suggested action. The one or more explanations may include (i) one or more most similar cases to the suggested case (e.g., the case associated with the suggested action) and, optionally, a conviction score for each nearby cases; (ii) action probabilities, (iii) excluding cases and distances, (iv) archetype and/or counterfactual cases for the suggested action; (v) feature residuals; (vi) regional model complexity; (vii) fractional dimensionality; (viii) prediction conviction; (ix) feature prediction contribution; and/or other measures such as the ones discussed herein, including certainty. In some embodiments, the explanation data may be used to determine whether to perform a suggested action.

Abstract: Machine learning feature engineering systems and methods comprise an event ingestion module that receives event data associated with entities. The ingestion module determines which entities are associated with events of the event data. The ingestion module stores the events, grouped by associated entity, in a related event store. A user defines features associated with the entities via an API and/or a feature studio. A feature computation layer determines values for the features based on the grouped events stored to the related event store. The feature computation layer stores the computed feature values and timestamps to a feature store. When new data is received, the feature computation layer computes one or more of the feature values for different times based on the timestamps. Feature vectors are generated using the computed feature values and output to the user via the API and/or feature studio.

Abstract: A compiler receives a description of a machine learning network and generates a computer program that implements the machine learning network. The computer program includes statically scheduled instructions that are executed by a mesh of processing elements (Tiles). The instructions executed by the Tiles are statically scheduled because the compiler can determine which instructions are executed by which Tiles at what times. For example, for the statically scheduled instructions, there are no conditions, branching or data dependencies that can be resolved only at run-time, and which would affect the timing and order of the execution of the instructions.

Abstract: Embodiments provide efficient, robust, and accurate programmatic prediction of optimized TCAD simulator system settings for future simulation executions to be performed by a TCAD simulation system.

Abstract: According to some embodiments, a method performed by a classification scanner comprises receiving an electronic message and determining a classification that applies to the electronic message. The classification is determined based on an express indication from a user. The method further comprises providing a machine learning trainer with the electronic message and an identification of the classification that applies to the electronic message. The machine learning trainer is adapted to determine a machine learning policy that associates attributes of the electronic message with the classification.

Abstract: A method, computer system, and a computer program product for automatic labeling to train a machine learning algorithm is provided. The present invention may include labeling a medical image with at least one finding from a corresponding medical report. The present invention may include determining a localization information from the labeled medical image. The present invention may include training the machine learning algorithm with the determined localization information. The present invention may include detecting at least one candidate in a test medical image. The present invention may include generating a discrepancy list between the at least one detected candidate in the test medical image and at least one human-reported finding in a corresponding test medical report. The present invention may include, in response to determining that the generated discrepancy list is above a threshold, retraining the trained machine learning algorithm until the generated discrepancy list is below the threshold.

Abstract: A compiler receives a description of a machine learning network and generates a computer program that implements the machine learning network. The computer program includes statically scheduled instructions that are executed by a mesh of processing elements (Tiles). The instructions executed by the Tiles are statically scheduled because the compiler can determine which instructions are executed by which Tiles at what times. For example, for the statically scheduled instructions, there are no conditions, branching or data dependencies that can be resolved only at run-time, and which would affect the timing and order of the execution of the instructions.

Abstract: Behavioral prediction for targeted end users is described. In one or more example embodiments, a computer-readable storage medium has multiple instructions that cause one or more processors to perform multiple operations. Targeted selectstream data is obtained from one or more indications of data object requests corresponding to a targeted end user. A targeted directed graph is constructed based on the targeted selectstream data. A targeted graph feature vector is computed based on one or more invariant features associated with the targeted directed graph. A behavioral prediction is produced for the targeted end user by applying a prediction model to the targeted graph feature vector. In one or more example embodiments, the prediction model is generated based on multiple graph feature vectors respectively corresponding to multiple end users. In one or more example embodiments, a tailored opportunity is determined responsive to the behavioral prediction and issued to the targeted end user.

Abstract: Aspects of the disclosure provide for mechanisms for providing optimization recommends for quantum computing. A method of the disclosure includes: receiving a first file including a first plurality of quantum instructions for implementing an algorithm; receiving hardware information of a plurality of quantum computer systems, wherein the hardware information comprises information about hardware capacities of the quantum computer systems; and generating, by a processing device, one or more optimization recommendations for implementing the algorithm in view of the first plurality of instructions and the hardware information. In some embodiments, the one or more optimization recommendations include an estimated qubit size required to implement the algorithm in at least one of the plurality of quantum computer systems.