Abstract: Techniques for input adaptation from disparate data sources for heterogeneous machine learning model execution are described. A preprocessing adapter can perform preprocessing of data obtained from edge devices to suit the input data characteristic requirements of one or more machine learning (ML) models. The preprocessing adapter can determine the input data characteristic requirements in a variety of ways, such as via analysis of the input layer of a ML model or through data variation testing and associated feedback resulting from output data generated by the ML model.

Abstract: Implementations detailed herein include description of a computer-implemented method.

Abstract: Techniques for machine learning (ML) model training and deployment using model building blocks via graphical user interfaces (GUIs) are described. Users can use a GUI provided by an electronic device to select and configure ML aspects for one or more ML models to be trained using identified training data. The electronic device can send a request to cause a model construction service to train one or more ML models based on the user configuration, return results of the training to the user within the GUI, and deploy one or more of the ML models.

Abstract: Techniques for generating and executing an execution plan for a machine learning (ML) model using one of an edge device and a non-edge device are described. In some examples, a request for the generation of the execution plan includes at least one objective for the execution of the ML model and the execution plan is generated based at least in part on comparative execution information and network latency information.

Abstract: A model selection and deployment service at a provider network receives an indication of sensor availability from a remote client device (e.g., what type of sensors are currently available to provide sensor data to the client device). The model selection and deployment service then selects, based on the sensor availability (and/or based on one or more other factors/criteria), a data processing model from a group of data processing models that are available for deployment to the client device. The model selection and deployment service then transmits the selected data processing model to the remote client device (e.g., for installation on the hub device). This may allow a client device to use the best data processing model for a sensor configuration and to dynamically adjust to any changes in the sensor configuration.

Abstract: Implementations detailed herein include description of a computer-implemented method. In an implementation, the method at least includes receiving an application instance configuration, an application of the application instance to utilize a portion of an attached accelerator during execution of a machine learning model and the application instance configuration including: an indication of the central processing unit (CPU) capability to be used, an arithmetic precision of the machine learning model to be used, an indication of the accelerator capability to be used, a storage location of the application, and an indication of an amount of random access memory to use.

Abstract: Techniques for utilizing adaptable filters for edge-based deep learning models are described. Filters may be utilized by an edge electronic device to filter elements of an input data stream so that only a subset of the elements are used as inputs to a machine learning model run by the electronic device, enabling successful operation despite the input data stream potentially being generated at a higher rate than a rate in which the ML model can be executed. The filter can be a differential-type filter that generates difference representations between consecutive elements of the data stream to determine which elements are to be passed on for the ML model, a “smart” filter such as a neural network trained using outputs from the ML model allowing the filter to “learn” which elements are the most likely to be of value to be passed on, or a combination of both.

Abstract: Implementations detailed herein include description of a computer-implemented method.

Abstract: Techniques for partitioning data flow operations between execution on a compute instance and an attached accelerator instance are described. A set of operations supported by the accelerator is obtained. A set of operations associated with the data flow is obtained. An operation in the set of operations associated with the data flow is identified based on the set of operations supported by the accelerator. The accelerator executes the first operation.

Abstract: Implementations detailed herein include description of a computer-implemented method. In an implementation, the method at least includes provisioning an application instance and portions of at least one accelerator attached to the application instance to execute a machine learning model of an application of the application instance; loading the machine learning model onto the portions of the at least one accelerator; receiving scoring data in the application; and utilizing each of the portions of the attached at least one accelerator to perform inference on the scoring data in parallel and only using one response from the portions of the accelerator.

Abstract: A processing device receives a dataset comprising a plurality of data points, wherein each data point of the plurality of data points comprises a representative vector for the data point and an associated classification for the data point. The processing device determines, for the dataset, a score representative of a degree of clustering of the plurality of data points. The processing device determines a suitability of the dataset for use in machine learning based on the score.

Abstract: Techniques are described for a nearest neighbor search service that enables users to perform nearest neighbor searches. The nearest neighbor search service includes an interface that enables users to create collections of searchable vectors, add and update vectors to a collection, delete vectors from a collection, and perform searches for nearest neighbors to a given vector. The nearest neighbor search service enables users to add, update, and delete vectors of a collection in real-time while also enabling users to perform searches at the same time.

Abstract: A data set may be partitioned according to relative differences indicated by a cover tree. A cover tree may be generated for a data set. Items in the data set may be stored at the same or different nodes according to the relative difference between the items indicated in the cover tree. Portions of the cover tree may be assigned to different nodes storing the data set. Access requests for the data set may be performed by sending the access requests to nodes identified according to the assigned portions of the cover tree.

Abstract: Techniques are described for a nearest neighbor search service that enables users to perform nearest neighbor searches. The nearest neighbor search service includes an interface that enables users to create collections of searchable vectors, add and update vectors to a collection, delete vectors from a collection, and perform searches for nearest neighbors to a given vector. The nearest neighbor search service enables users to add, update, and delete vectors of a collection in real-time while also enabling users to perform searches at the same time.

Abstract: Techniques are described for a nearest neighbor search service that enables users to perform nearest neighbor searches. The nearest neighbor search service includes an interface that enables users to create collections of searchable vectors, add and update vectors to a collection, delete vectors from a collection, and perform searches for nearest neighbors to a given vector. The nearest neighbor search service enables users to add, update, and delete vectors of a collection in real-time while also enabling users to perform searches at the same time.

Abstract: A computing resource service provider deploys resources to process input data sets on an ongoing basis and provide requestors with queryable data structures generated from the input data sets over determined, rolling periods of time. In one embodiment, the input data sets are processed using one or more nearest neighbor search algorithms, and the outputs therefrom are represented in data structures which are rotated as newer data structures are subsequently generated. The disclosed systems and techniques improve resource utilization, processing efficiency, query latency, and result consistency relative to known controls for large and/or complex data processing tasks, such as those employed in machine learning techniques.

Abstract: A computing resource service provider deploys resources to process input data sets on an ongoing basis and provide requestors with queryable data structures generated from the input data sets over determined, rolling periods of time. In one embodiment, the input data sets are processed using one or more nearest neighbor search algorithms, and the outputs therefrom are represented in data structures which are rotated as newer data structures are subsequently generated. The disclosed systems and techniques improve resource utilization, processing efficiency, query latency, and result consistency relative to known controls for large and/or complex data processing tasks, such as those employed in machine learning techniques.

Abstract: Implementations detailed herein include description of a computer-implemented method to migrate a machine learning model from one accelerator portion (such as a portion of a graphical processor unit (GPU)) to a different accelerator portion. In some instances, a state of the first accelerator portion is persisted, the second accelerator portion is configured, the first accelerator portion is then detached from a client application instance, and at least a portion of an inference request is performed using the loaded at least a portion of the machine learning model on the second accelerator portion that had been configured.

Abstract: Techniques for intelligent coalescing of media streams are described. A coalesce engine receives multiple media streams, such as audio or video streams, that are misaligned. The coalesce engine can analyze the media streams by comparing representations of elements of the media streams to detect the misalignment. The coalesce engine may determine an offset amount representing the misalignment, and if the offset amount meets or exceeds a threshold the coalesce engine can work to eliminate the misalignment by introducing one or more artificial delays before sending elements of ones of the media streams that are “ahead” of others of the streams. The coalese engine can additionally or alternatively send feedback to sources of the media streams, causing the source(s) to attempt to mitigate the misalignment.

Abstract: A data set may be partitioned according to relative differences indicated by a cover tree. A cover tree may be generated for a data set. Items in the data set may be stored at the same or different nodes according to the relative difference between the items indicated in the cover tree. Portions of the cover tree may be assigned to different nodes storing the data set. Access requests for the data set may be performed by sending the access requests to nodes identified according to the assigned portions of the cover tree.