公开(公告)号：US09792530B1

公开(公告)日：2017-10-17

申请号：US14980898

申请日：2015-12-28

Applicant: Amazon Technologies, Inc.

Inventor： Weixin Wu ,  Wei Xia ,  Meng Wang ,  Ranju Das

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06K9/46

CPC classification number: G06K9/6253 ,  G06K9/46 ,  G06K9/6267 ,  G06N3/0427 ,  G06N3/084

Abstract: A knowledge base (KB) is generated and used to classify images. The knowledge base includes a number subcategories of a specified category. Instead of obtaining images just based on a category name, structured and unstructured data sources are used to identify subcategories of the category. Subcategories that are determined to not be relevant to the category may be removed. The remaining data may be used to generate the KB. After identifying the relevant subcategories, representative images are obtained from one or more image sources based on the subcategories identified by the KB. The obtained images and the KB are then used to train an image classifier, such as a neural network or some other machine learning mechanism. After training, the neural network might, for example, classify an object within an image of a car, as a car, but also as a particular brand and model type.

公开(公告)号：US20210034980A1

公开(公告)日：2021-02-04

申请号：US17073147

申请日：2020-10-16

Applicant: Amazon Technologies, Inc.

Inventor： Wei Xia ,  Weixin Wu ,  Meng Wang ,  Ranju Das

IPC: G06N3/08 ,  G06N3/04

Abstract: A visualization tool for machine learning models obtains metadata from a first training node at which a multi-layer machine learning model is being trained. The metadata includes a parameter of an internal layer of the model. The tool determines a plurality of metrics from the metadata, including respective loss function values corresponding to several training iterations of the model. The tool indicates the loss function values and the internal layer parameter values via a graphical interface.

公开(公告)号：US12198046B2

公开(公告)日：2025-01-14

申请号：US17073147

申请日：2020-10-16

Applicant: Amazon Technologies, Inc.

Inventor： Wei Xia ,  Weixin Wu ,  Meng Wang ,  Ranju Das

IPC: G06N3/08 ,  G06N3/04

Abstract: A visualization tool for machine learning models obtains metadata from a first training node at which a multi-layer machine learning model is being trained. The metadata includes a parameter of an internal layer of the model. The tool determines a plurality of metrics from the metadata, including respective loss function values corresponding to several training iterations of the model. The tool indicates the loss function values and the internal layer parameter values via a graphical interface.

公开(公告)号：US10810491B1

公开(公告)日：2020-10-20

申请号：US15074203

申请日：2016-03-18

Applicant: Amazon Technologies, Inc.

Inventor： Wei Xia ,  Weixin Wu ,  Meng Wang ,  Ranju Das

IPC: G06N3/08 ,  G06N3/04

Abstract: A visualization tool for machine learning models obtains metadata from a first training node at which a multi-layer machine learning model is being trained. The metadata includes a parameter of an internal layer of the model. The tool determines a plurality of metrics from the metadata, including respective loss function values corresponding to several training iterations of the model. The tool indicates the loss function values and the internal layer parameter values via a graphical interface.

公开(公告)号：US10467290B1

公开(公告)日：2019-11-05

申请号：US14982816

申请日：2015-12-29

Applicant: Amazon Technologies, Inc.

Inventor： Weixin Wu ,  Wei Xia ,  Ranju Das ,  Meng Wang

IPC: G06F16/901 ,  G06F16/58

Abstract: A knowledge graph (KG) is generated and refined. The generated KG describes direct relationships between different words associated with a particular classification. Initially, a semantic data source, such as a lexical database, is accessed to identify words that are similarly grouped and express a distinct concept. A KG generator creates a sparse KG that provides a direct connection between a seed word and other words. The sparse KG is used by a dense KG generator to create a dense KG. The dense KG generator creates a dense KG that joins each of the different words directly with the seed word for the category. At different points during the creation and refinement of the KG, a user may add or remove one or more connections that affect the creation of the KG.

公开(公告)号：US11875250B1

公开(公告)日：2024-01-16

申请号：US15627330

申请日：2017-06-19

Applicant: Amazon Technologies, Inc.

Inventor： Wei Xia ,  Meng Wang ,  Weixin Wu

IPC: G06N3/08 ,  G06N3/04 ,  G06F16/583

CPC classification number: G06N3/08 ,  G06F16/583 ,  G06N3/04

Abstract: An indication of semantic relationships among classes is obtained. A neural network whose loss function is based at least partly on the semantic relationships is trained. The trained neural network is used to identify one or more classes to which an input observation belongs.