Amazon Technologies, Inc.

Other

Robert Matthias Steele

Jin Li

Sriram Krishnan

Donghui Zhuo

Charles Eric Dannaker

Sudhakar Rao Puvvadi

Daniel Blick

Rakesh Ramakrishnan

Polly Po Lee

Ralf Herbrich

Michael Brueckner

Leo Parker Dirac

Saman Zarandioon

Gerard Guy Medioni

Nishitkumar Ashokkumar Desai

Jayakrishnan Kumar Eledath

Jean Laurent Guigues

Nicolle M Correa

Pahal Kamlesh Dalal

Kartik Muktinutalapati

Alessandro Bergamo

Tianming Zheng

Lu Xia

Marian Nasr Amin George

James Joseph Jesensky

Aleksandr Mikhaylovich Ingerman

Steven Andrew Loeppky

Tarun Agarwal

Polly Po Yee Lee

Jun Qian

Respective statistical distributions of a target variable within a proposed training data set and a proposed test data set for a machine learning model are obtained. A metric indicative of the difference between the two statistical distributions is computed. The difference metric is used to determine whether the proposed test data set is acceptable to evaluate the machine learning model.

Target variable distribution-based acceptance of machine learning test data sets

In a materials handling facility, events may be associated with users based on imaging data captured from multiple fields of view. When an event is detected at a location within the fields of view of multiple cameras, two or more of the cameras may be identified as having captured images of the location at a time of the event. Users within the materials handling facility may be identified from images captured prior to, during or after the event, and visual representations of the respective actors may be generated from the images. The event may be associated with one of the users based on distances between the users' hands and the location of the event, as determined from the visual representations, or based on imaging data captured from the users' hands, which may be processed to determine which, if any, of such hands includes an item associated with the event.

Associating items with actors based on digital imagery

Associating events with actors based on digital imagery

A determination that a machine learning data set is to be shuffled is made. Tokens corresponding to the individual observation records are generated based on respective identifiers of the records' storage objects and record key values. Respective representative values are derived from the tokens. The observation records are rearranged based on a result of sorting the representative values and provided to a shuffle result destination.

Consistent sort-based record-level shuffling of machine learning data

A request to split a data set comprising observation records located in a group of storage objects is received. With respect to a particular observation record, a token is generated based on an identifier of the record's storage object and a key value of the record. A numeric value is calculated using the token, and the observation record is assigned to a split subset using the numeric value. An indication of the assignment is provided to a destination associated with the split subset.

Consistent randomized record-level splitting of machine learning data

During a training phase of a machine learning model, representations of at least some nodes of a decision tree are generated and stored on persistent storage in depth-first order. A respective predictive utility metric (PUM) value is determined for one or more nodes, indicating expected contributions of the nodes to a prediction of the model. A particular node is selected for removal from the tree based at least partly on its PUM value. A modified version of the tree, with the particular node removed, is stored for obtaining a prediction.

Optimized decision tree based models

An apparatus, in combination with a conventional electrically powered hand or rider lawn mower, which provides a detachable electrical power source for such lawn mowers and one or more auxiliary electrical hand tools. The apparatus has an electrical generator powered by a gasoline engine and a control box all of which are mounted by support elements on a rectangular shaped tubular frame. The tubular frame is attached by four or more retention clips to the protective shroud of a hand lawn mower or the rear deck of a rider lawn mower. The control box has two or more a.c. electrical outlets which can be used to feed electrical current to the lawn mower and/or auxiliary electrical hand tools such as weed eaters, blowers, hedge clippers or edgers. In an alternative mode, the apparatus can be temporarily removed from the lawn mowers for use with a Recreational Vehicle, a lighting system or outdoor pump.

Gasoline powered electrical lawn mower

Growing community of inventors

Seattle, WA, United States of America

Robert Matthias Steele