BR112018006288A2 - retropropagação seletiva - Google Patents

retropropagação seletiva

Info

Publication number
BR112018006288A2
BR112018006288A2 BR112018006288A BR112018006288A BR112018006288A2 BR 112018006288 A2 BR112018006288 A2 BR 112018006288A2 BR 112018006288 A BR112018006288 A BR 112018006288A BR 112018006288 A BR112018006288 A BR 112018006288A BR 112018006288 A2 BR112018006288 A2 BR 112018006288A2
Authority
BR
Brazil
Prior art keywords
gradient
class
back propagation
selective back
examples
Prior art date
Application number
BR112018006288A
Other languages
English (en)
Inventor
Jonathan Julian David
Blythe Towal Regan
Original Assignee
Qualcomm Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Qualcomm Inc filed Critical Qualcomm Inc
Publication of BR112018006288A2 publication Critical patent/BR112018006288A2/pt

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/047—Probabilistic or stochastic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
    • G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
    • G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Abstract

o equilíbrio de dados de treinamento entre classes para um modelo de aprendizado de máquina é modificado. ajustes são feitos na etapa de gradiente onde a retropropagação seletiva é utilizada para modificar uma função de custo para ajustar ou aplicar, seletivamente, o gradiente com base na frequência de exemplo de classe nas configurações de dados. o fator para modificação do gradiente pode ser determinado com base em uma razão do número de exemplos de classes com o menor número de elementos sobre o número de exemplos de uma classe atual. o gradiente associado com a classe atual é baseado no fator determinado acima.
BR112018006288A 2015-09-29 2016-09-07 retropropagação seletiva BR112018006288A2 (pt)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US201562234559P 2015-09-29 2015-09-29
US15/081,780 US20170091619A1 (en) 2015-09-29 2016-03-25 Selective backpropagation
PCT/US2016/050539 WO2017058479A1 (en) 2015-09-29 2016-09-07 Selective backpropagation

Publications (1)

Publication Number Publication Date
BR112018006288A2 true BR112018006288A2 (pt) 2018-10-16

Family

ID=58407414

Family Applications (1)

Application Number Title Priority Date Filing Date
BR112018006288A BR112018006288A2 (pt) 2015-09-29 2016-09-07 retropropagação seletiva

Country Status (7)

Country Link
US (1) US20170091619A1 (pt)
EP (1) EP3357003A1 (pt)
JP (1) JP6859332B2 (pt)
KR (1) KR102582194B1 (pt)
CN (1) CN108140142A (pt)
BR (1) BR112018006288A2 (pt)
WO (1) WO2017058479A1 (pt)

Families Citing this family (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11250335B2 (en) * 2015-10-26 2022-02-15 NetraDyne, Inc. Joint processing for embedded data inference
US10970605B2 (en) * 2017-01-03 2021-04-06 Samsung Electronics Co., Ltd. Electronic apparatus and method of operating the same
US11003989B2 (en) 2017-04-27 2021-05-11 Futurewei Technologies, Inc. Non-convex optimization by gradient-accelerated simulated annealing
CN107229968B (zh) * 2017-05-24 2021-06-29 北京小米移动软件有限公司 梯度参数确定方法、装置及计算机可读存储介质
US11517768B2 (en) * 2017-07-25 2022-12-06 Elekta, Inc. Systems and methods for determining radiation therapy machine parameter settings
US11556794B2 (en) * 2017-08-31 2023-01-17 International Business Machines Corporation Facilitating neural networks
WO2019070300A1 (en) * 2017-10-06 2019-04-11 Google Llc SYSTEMS AND METHODS FOR IMAGE SWITCHING
US11615129B2 (en) * 2017-11-28 2023-03-28 International Business Machines Corporation Electronic message text classification framework selection
US11461631B2 (en) * 2018-03-22 2022-10-04 Amazon Technologies, Inc. Scheduling neural network computations based on memory capacity
US11475306B2 (en) 2018-03-22 2022-10-18 Amazon Technologies, Inc. Processing for multiple input data sets
US20190303176A1 (en) * 2018-03-29 2019-10-03 Qualcomm Incorporated Using Machine Learning to Optimize Memory Usage
US11281999B2 (en) * 2019-05-14 2022-03-22 International Business Machines Corporation Armonk, New York Predictive accuracy of classifiers using balanced training sets
JP7295710B2 (ja) * 2019-06-07 2023-06-21 ジオテクノロジーズ株式会社 学習用画像データ生成装置
WO2021040944A1 (en) 2019-08-26 2021-03-04 D5Ai Llc Deep learning with judgment
US20210065054A1 (en) * 2019-09-03 2021-03-04 Koninklijke Philips N.V. Prioritizing tasks of domain experts for machine learning model training
US20210089924A1 (en) * 2019-09-24 2021-03-25 Nec Laboratories America, Inc Learning weighted-average neighbor embeddings
JP7268924B2 (ja) * 2019-11-14 2023-05-08 株式会社アクセル 推論システム、推論装置、推論方法及び推論プログラム
US11077320B1 (en) 2020-02-07 2021-08-03 Elekta, Inc. Adversarial prediction of radiotherapy treatment plans
WO2023069973A1 (en) * 2021-10-19 2023-04-27 Emory University Selective backpropagation through time

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5142135B2 (ja) * 2007-11-13 2013-02-13 インターナショナル・ビジネス・マシーンズ・コーポレーション データを分類する技術
CN103763350A (zh) * 2014-01-02 2014-04-30 北京邮电大学 基于误差反向传播神经网络的web服务选择方法

Also Published As

Publication number Publication date
EP3357003A1 (en) 2018-08-08
JP6859332B2 (ja) 2021-04-14
JP2018533138A (ja) 2018-11-08
KR102582194B1 (ko) 2023-09-22
KR20180063189A (ko) 2018-06-11
WO2017058479A1 (en) 2017-04-06
US20170091619A1 (en) 2017-03-30
CN108140142A (zh) 2018-06-08

Similar Documents

Publication Publication Date Title
BR112018006288A2 (pt) retropropagação seletiva
BR112018002040A2 (pt) controle de uma nuvem de dispositivo
BR112016024506A2 (pt) inversão rápida de campo de onda viscoacústica e viscoelástica total
BR112018003434A2 (pt) método para aperfeiçoamento de desempenho de um modelo de aprendizagem de máquina treinado
BR112018001162A2 (pt) estrutura de sub-quadro duplex por divisão de tempo (tdd) que suporta modos de entrelaçamento único e múltiplo
BR112015026673A2 (pt) método e sistema para sincronização com vizinho em um grupo de agregação de link com interconexão de rede resiliente distribuída (drni)
BR112015018922A8 (pt) dispositivo, método e um ou mais meios de armazenamento não transitórios legíveis por computador para estimação de rotina
CL2018001293A1 (es) Equipo de autoservicio método y dispositivo de control de ahorro de energía y dispositivo
BR112016017406A2 (pt) Método e dispositivo para determinar um modelo ambiental de dimensão n+1 e aparelho de prospecção
MX2020003605A (es) Manipulación del metabolismo de triptamina.
BR112017010078A2 (pt) composições, dispositivos e métodos de teste de sensibilidade de ibs
BR112015018696A2 (pt) rotulagem de padrão
BR112019007580A2 (pt) avaliação e mitigação de risco e perigo geomecânico
BR112017009953A2 (pt) sistemas e métodos de controle adequados para utilização com sistemas e métodos de produção de energia
EP3002649A3 (en) Industrial simulation using redirected i/o module configurations
BR112017010556A2 (pt) suportes passivados: catalisador, processo, produto e película
EA201690296A1 (ru) Способ адаптации геологического представления геологической среды
BR112016001923A2 (pt) método implementado por computador, meio legível por computador não transitório e sistema para realizar simulações de fluxo de árvore declassificação e regressão (cart) para um reservatório
MX2023006660A (es) Composiciones, dispositivos, y metodos de pruebas de sensibilidad a la osteoartritis.
IN2014CH00698A (pt)
BR112016023520A2 (pt) gestão de temperatura em arranjos de bateria
BR112018011010A2 (pt) dispositivo de rede compreendendo uma estação base e uma estação de docagem e uma respectiva estação de base e uma estação de docagem
BR112017023699A2 (pt) métodos e sistemas para uso no monitoramento das operações de um negócio
BR112017000915A2 (pt) divisor de tensão rc
MX2019000649A (es) Composiciones y metodos para marcar composiciones de hidrocarburos con tintas no mutagenicas.

Legal Events

Date Code Title Description
B06U Preliminary requirement: requests with searches performed by other patent offices: procedure suspended [chapter 6.21 patent gazette]
B07A Application suspended after technical examination (opinion) [chapter 7.1 patent gazette]
B09B Patent application refused [chapter 9.2 patent gazette]
B12B Appeal against refusal [chapter 12.2 patent gazette]