Abstract: Techniques for determining an absolute longitudinal position of a moving object on non-linear sections of a trajectory are described. In one technique, an estimated track boundary segment is generated based on a digital image associated with a moving object. For each position of multiple positions in an actual track boundary segment pertaining to a track for one or more moving objects, an alignment of the estimated track boundary segment with the actual track boundary segment is made based on that position. Also, based on the alignment, a difference measurement between the estimated track boundary segment and a portion of the actual track boundary segment is generated. After each of the positions is considered, a particular alignment, of multiple alignments, that is associated with the lowest difference measurement among the multiple positions is selected. Based on the particular alignment, a longitudinal value of the moving object is determined.

Abstract: Techniques for preparing data for high-precision absolute localization of a moving object along a trajectory are provided. In one technique, a sequence of points is stored, where each point corresponds to a different set of Cartesian coordinates. A curve is generated that approximates a line that passes through the sequence of points. Based on the curve, a set of points is generated on the curve, where the set of points is different than the sequence of points. New Cartesian coordinates are generated for each point in the set of points. After generating the new Cartesian coordinates, Cartesian coordinates of a position of a moving object are determined.

Abstract: Techniques for preparing data for high-precision absolute localization of a moving object along a trajectory are provided. In one technique, a sliding window of a set of adjacent points along a trajectory of a moving object is identified, along with a midpoint in the sliding window. Based on the set of adjacent points, a first polynomial equation is generated for a first dimension and a second polynomial equation is generated for a second dimension. A first derivative at a particular timestamp associated with the midpoint is a first velocity along the first dimension, while a particular first derivative at the particular timestamp is a second velocity along the second dimension. A velocity in direction of yaw is generated based on the first velocity, the second velocity, and a slip angle associated with the midpoint. A yaw angle is generated based on the velocity in direction of yaw.

Abstract: Techniques for deriving an optimal traversal path on a racetrack are disclosed. The system partitions a track into straight and curved segments. The system identifies optimal traversals through each segment from historical traversal data. The system stitches the optimal traversals together and smooths the optimal traversals at the transition points between track segments. The system verifies that the smoothed traversals meet one or more kinematic criteria before outputting the optimal traversal path.

Abstract: The present disclosure relates to systems and methods for an adaptive pipelining composition service that can identify and incorporate one or more new models into the machine learning application. The machine learning application with the new model can be tested off-line with the results being compared with ground truth data. If the machine learning application with the new model outperforms the previously used model, the machine learning application can be upgraded and auto-promoted to production. One or more parameters may also be discovered. The new parameters may be incorporated into the existing model in an off-line mode. The machine learning application with the new parameters can be tested off-line and the results can be compared with previous results with existing parameters. If the new parameters outperform the existing parameters as compared with ground-truth data, the machine learning application can be auto-promoted to production.

Abstract: Techniques for smoothing a signal are disclosed. The system partitions the portion of the data sequence into a stable subsequence and an unstable subsequence of data points. The system applies a rate of change exhibited by the stable subsequence to the unstable subsequence to create a smoothed, more stable subsequence.

Abstract: Techniques for generating high-precision localization of a moving object on a trajectory are provided. In one technique, a particular image that is associated with a moving object is identified. A set of candidate images is selected from a plurality of images that were used to train a neural network. For each candidate image in the set of candidate images: (1) output from the neural network is generated based on inputting the particular image and said each candidate image to the neural network; (2) a predicted position of the particular image is determined based on the output and a position that is associated with said each candidate image; and (3) the predicted position is added to a set of predicted positions. The set of predicted positions is aggregated to generate an aggregated position for the particular image.

Abstract: The present disclosure relates to systems and methods for an adaptive pipelining composition service that can identify and incorporate one or more new models into the machine learning application. The machine learning application with the new model can be tested off-line with the results being compared with ground truth data. If the machine learning application with the new model outperforms the previously used model, the machine learning application can be upgraded and auto-promoted to production. One or more parameters may also be discovered. The new parameters may be incorporated into the existing model in an off-line mode. The machine learning application with the new parameters can be tested off-line and the results can be compared with previous results with existing parameters. If the new parameters outperform the existing parameters as compared with ground-truth data, the machine learning application can be auto-promoted to production.

Abstract: A server system may receive two or more Quality of Service (QoS) dimensions for the multi-objective optimization model, wherein the two or more QoS dimensions include at least a first QoS dimension and a second QoS dimension. The server system may maximize the multi-objective optimization model along the first QoS dimension, wherein the maximizing includes selecting one or more pipelines for the multi-objective optimization model in the software architecture that meet QoS expectations specified for the first QoS dimension and the second QoS dimension, wherein an ordering of the pipelines is dependent on which QoS dimensions were optimized and de-optimized and to what extent, wherein the multi-objective optimization model is partially de-optimized along the second QoS dimension in order to comply with the QoS expectations for the first QoS dimension, and whereby there is a tradeoff between the first QoS dimension and the second QoS dimension.

Abstract: A server system may receive two or more Quality of Service (QoS) dimensions for the multi-objective optimization model, wherein the two or more QoS dimensions include at least a first QoS dimension and a second QoS dimension. The server system may maximize the multi-objective optimization model along the first QoS dimension, wherein the maximizing includes selecting one or more pipelines for the multi-objective optimization model in the software architecture that meet QoS expectations specified for the first QoS dimension and the second QoS dimension, wherein an ordering of the pipelines is dependent on which QoS dimensions were optimized and de-optimized and to what extent, wherein the multi-objective optimization model is partially de-optimized along the second QoS dimension in order to comply with the QoS expectations for the first QoS dimension, and whereby there is a tradeoff between the first QoS dimension and the second QoS dimension.

Abstract: A server system can receive an input identifying a problem to generate a solution using a machine-learning application. The method selects a machine-learning model template from a plurality of templates based at least in part on the input. The method analyzes one or more formats of the customer data to generate a customer data schema based at least in part a data ontology that applies to the identified problem. The method determines whether the customer data schema is misaligned with one or more key features of the selected machine-learning model template. Based on this determination, the method analyzes the metadata for the selected machine-learning model template to determine what additional information is required to re-align the customer data with the data expectations. The method can include gathering the addition information required to re-align the customer data with the data expectations of the selected machine-learning model template.

Abstract: The present disclosure relates to systems and methods for an intelligent assistant (e.g., a chatbot) that can be used to enable a user to generate a machine learning system. Techniques can be used to automatically generate a machine learning system to assist a user. In some cases, the user may not be a software developer and may have little or no experience in either machine learning techniques or software programming. In some embodiments, a user can interact with an intelligent assistant. The interaction can be aural, textual, or through a graphical user interface. The chatbot can translate natural language inputs into a structural representation of a machine learning solution using an ontology. In this way, a user can work with artificial intelligence without being a data scientist to develop, train, refine, and compile machine learning models as stand-alone executable code.

Abstract: The present disclosure relates to systems and methods for a machine-learning platform for the safe serialization of a machine-learning application. Individual library components (e.g., a pipeline, a microservice routine, a software module, and an infrastructure model) can be encrypted using one or more keys. The keys can be stored in a location different from the storage location of the machine-learning application. Prior to incorporation of the library component into a machine-learning model, one or more keys can be retrieved from the remote storage location to authenticate that the one or more encrypted library components are authentic. The process can reject any of the one or more component, when the encrypted library component fails authentication. If a component is rejected, the system can roll back to a previous, authenticated version of the library component. The authenticated library components can be compiled into machine-learning software.

Abstract: The present disclosure relates to systems and methods for an adaptive pipelining composition service that can identify and incorporate one or more new models into the machine learning application. The machine learning application with the new model can be tested off-line with the results being compared with ground truth data. If the machine learning application with the new model outperforms the previously used model, the machine learning application can be upgraded and auto-promoted to production. One or more parameters may also be discovered. The new parameters may be incorporated into the existing model in an off-line mode. The machine learning application with the new parameters can be tested off-line and the results can be compared with previous results with existing parameters. If the new parameters outperform the existing parameters as compared with ground-truth data, the machine learning application can be auto-promoted to production.

Abstract: The present disclosure relates to systems and methods for a machine learning platform that generates a library of components to generate machine learning models and machine learning applications. The machine learning infrastructure system allows a user (i.e., a data scientist) to generate machine learning applications without having detailed knowledge of the cloud-based network infrastructure or knowledge of how to generate code for building the model. The machine learning platform can analyze the identified data and the user provided desired prediction and performance characteristics to select one or more library components and associated API to generate a machine learning application. The machine learning can monitor and evaluate the outputs of the machine learning model to allow for feedbacks and adjustments to the model. The machine learning application can be trained, tested, and compiled for export as stand-alone executable code.

Abstract: The present disclosure relates to systems and methods for an intelligent assistant (e.g., a chatbot) that can be used to enable a user to generate a machine learning system. Techniques can be used to automatically generate a machine learning system to assist a user. In some cases, the user may not be a software developer and may have little or no experience in either machine learning techniques or software programming. In some embodiments, a user can interact with an intelligent assistant. The interaction can be aural, textual, or through a graphical user interface. The chatbot can translate natural language inputs into a structural representation of a machine learning solution using an ontology. In this way, a user can work with artificial intelligence without being a data scientist to develop, train, refine, and compile machine learning models as stand-alone executable code.

Abstract: A computer-implemented method in a computing network of a number of processing nodes 1 to X, in the computing network neurons of a Convolutional Neural Network (CNN) are divided between the number of nodes. The method including allocating a mini-batch of input data from among mini-batches of input data to a node of the nodes; splitting the mini-batch into a number of mini-batch sections X corresponding and equal to the number of nodes; at the node retaining a mini-batch section which has a same number as the node and sending other mini-batch sections of the split mini-batch sections to corresponding other nodes according to a number of the split mini-batch sections; collating at the node the split mini-batch sections at the node into a single matrix and multiplying the collated matrix by the neurons to provide output data sections having one section of output data per each mini-batch.

Abstract: The present disclosure relates to systems and methods for a machine learning platform that generates a library of components to generate machine learning models and machine learning applications. The machine learning infrastructure system allows a user (i.e., a data scientist) to generate machine learning applications without having detailed knowledge of the cloud-based network infrastructure or knowledge of how to generate code for building the model. The machine learning platform can analyze the identified data and the user provided desired prediction and performance characteristics to select one or more library components and associated API to generate a machine learning application. The machine learning can monitor and evaluate the outputs of the machine learning model to allow for feedbacks and adjustments to the model. The machine learning application can be trained, tested, and compiled for export as stand-alone executable code.

Abstract: The present disclosure relates to systems and methods for an adaptive pipelining composition service that can identify and incorporate one or more new models into the machine learning application. The machine learning application with the new model can be tested off-line with the results being compared with ground truth data. If the machine learning application with the new model outperforms the previously used model, the machine learning application can be upgraded and auto-promoted to production. One or more parameters may also be discovered. The new parameters may be incorporated into the existing model in an off-line mode. The machine learning application with the new parameters can be tested off-line and the results can be compared with previous results with existing parameters. If the new parameters outperform the existing parameters as compared with ground-truth data, the machine learning application can be auto-promoted to production.

Abstract: The present disclosure relates to systems and methods for an intelligent assistant (e.g., a chatbot) that can be used to enable a user to generate a machine learning system. Techniques can be used to automatically generate a machine learning system to assist a user. In some cases, the user may not be a software developer and may have little or no experience in either machine learning techniques or software programming. In some embodiments, a user can interact with an intelligent assistant. The interaction can be aural, textual, or through a graphical user interface. The chatbot can translate natural language inputs into a structural representation of a machine learning solution using an ontology. In this way, a user can work with artificial intelligence without being a data scientist to develop, train, refine, and compile machine learning models as stand-alone executable code.