Amazon Technologies, Inc.

Romi Boimer

Poorna Chand Srinivas Perumalla

Gopinath Duddi

Madan Mohan Rao Jampani

Nagajyothi Nookula

Eduardo Manuel Calleja

Safeer Mohiuddin

Aashish Jindia

Vinay Hanumaiah

Amit Gul Phagwani

Ronald Stephen Kyker

Surbhi Dangi

Danjuan Ye

Song Ge

Wanqiang Chen

Fei Chen

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

Techniques for visual data preparation are described. An interactive visual data preparation service provides a user with a graphical user interface that presents values from a sample taken of a dataset along with statistical information associated with those values. A user uses the graphical user interface to test out various transformations to the sample dataset by applying transformations and viewing near-immediate results of those transformations as applied to the sample. The desired set of transformations is represented as a recipe object, which can be used to perform data preparation against the overall dataset or other datasets on behalf of the user or other users.

Interactive visual data preparation service

Growing community of inventors

Newark, CA, United States of America

Romi Boimer