Amazon Technologies, Inc.

Eduardo Manuel Calleja

Poorna Chand Srinivas Perumalla

Nagajyothi Nookula

Vinay Hanumaiah

Aashish Jindia

Long Gao

Gang Chen

Madan Mohan Rao Jampani

Safeer Mohiuddin

Romi Boimer

Danjuan Ye

Song Ge

Wanqiang Chen

Fei Chen

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.

Intelligent input adaptation from disparate data sources for heterogeneous machine learning model execution

Techniques for high-performance machine learning (ML) inference in heterogenous edge devices are described. A ML model trained using a variety of different frameworks is translated into a common format that is runnable by inferences engines of edge devices. The translated model is optimized in hardware-agnostic and/or hardware-specific ways to improve inference performance, and the optimized model is sent to the edge devices. The inference engine for any edge device can be accessed by a customer application using a same defined API, regardless of the hardware characteristics of the edge device or the original format of the ML model.

High performance machine learning inference framework for edge devices

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.

Automated distribution of models for execution on a non-edge device and an edge device

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.

Selecting and deploying models based on sensor availability

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.

Adaptable filtering for edge-based deep learning models

High perforamance machine learning inference framework for edge devices

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.

Growing community of inventors

San Francisco, CA, United States of America

Eduardo Manuel Calleja