BR112018003434A2 - método para aperfeiçoamento de desempenho de um modelo de aprendizagem de máquina treinado - Google Patents

método para aperfeiçoamento de desempenho de um modelo de aprendizagem de máquina treinado

Info

Publication number
BR112018003434A2
BR112018003434A2 BR112018003434A BR112018003434A BR112018003434A2 BR 112018003434 A2 BR112018003434 A2 BR 112018003434A2 BR 112018003434 A BR112018003434 A BR 112018003434A BR 112018003434 A BR112018003434 A BR 112018003434A BR 112018003434 A2 BR112018003434 A2 BR 112018003434A2
Authority
BR
Brazil
Prior art keywords
machine learning
learning model
trained machine
performance improvement
classifier
Prior art date
Application number
BR112018003434A
Other languages
English (en)
Other versions
BR112018003434B1 (pt
Inventor
Vartak Aniket
Subhash Talathi Sachin
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 BR112018003434A2 publication Critical patent/BR112018003434A2/pt
Publication of BR112018003434B1 publication Critical patent/BR112018003434B1/pt

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • 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
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • 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
    • G06N3/048—Activation functions
    • 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
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
    • 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
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic 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
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • 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
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
    • G06V10/7747—Organisation of the process, e.g. bagging or boosting
    • 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
    • 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
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Multimedia (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Databases & Information Systems (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Algebra (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Image Analysis (AREA)
  • Feedback Control In General (AREA)

Abstract

um método para melhorar o desempenho de um modelo de aprendizagem de máquina treinado inclui adicionar um segundo classificador com uma segunda função objetiva a um primeiro classificador com uma primeira função objetiva. em vez de minimizar uma função de erros para o primeiro classificador, a segunda função objetiva é usada para reduzir diretamente os erros de número do primeiro classificador.
BR112018003434-7A 2015-08-25 2016-08-11 Método implementado em computador e aparelho para melhorar desempenho de um modelo de aprendizagem de máquina treinado para reconhecimento de padrão ou objeto de uma imagem e memória legível por computador BR112018003434B1 (pt)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US201562209859P 2015-08-25 2015-08-25
US62/209,859 2015-08-25
US14/863,410 US10332028B2 (en) 2015-08-25 2015-09-23 Method for improving performance of a trained machine learning model
US14/863,410 2015-09-23
PCT/US2016/046576 WO2017034820A1 (en) 2015-08-25 2016-08-11 Method for improving performance of a trained machine learning model

Publications (2)

Publication Number Publication Date
BR112018003434A2 true BR112018003434A2 (pt) 2018-09-25
BR112018003434B1 BR112018003434B1 (pt) 2024-04-16

Family

ID=

Also Published As

Publication number Publication date
CN108027899B (zh) 2023-02-24
US20170061326A1 (en) 2017-03-02
JP6862426B2 (ja) 2021-04-21
EP3341894A1 (en) 2018-07-04
CN108027899A (zh) 2018-05-11
WO2017034820A1 (en) 2017-03-02
US10332028B2 (en) 2019-06-25
KR20180044295A (ko) 2018-05-02
JP2018529159A (ja) 2018-10-04

Similar Documents

Publication Publication Date Title
BR112018002040A2 (pt) controle de uma nuvem de dispositivo
BR112018009393A2 (pt) produção microbiana de nicotinamida ribosídeo
DOP2016000337A (es) Compuestos heterociclicos y su uso como inhibidores de gamma-t del receptor orfano relacionados con retinoide (ror)
BR112016001904A2 (pt) método para determinar um valor ideal para um controle de uma operação de perfuração
BR112017027137A2 (pt) reguladores de nrf2
BR112017008270A2 (pt) aprimoramentos de mac para operação herdada e de ecc concomitante
BR112017018133A2 (pt) "sistemas e métodos para coordenar o processamento de dados por múltiplos recursos de computação em rede, e meio legível por computador."
UY36315A (es) COMPUESTOS NOVEDOSOS ANTAGONISTAS DE INTEGRINA avß6.
BR112018002461A2 (pt) compostos para dispositivos opticamente ativos
TWD183605S (zh) 鍵盤之部分
BR112017013103A2 (pt) porca segmentada
BR112016030948A2 (pt) Método para simulação do tempo necessário para executar uma operação marítima restrita ao clima
BR112017009953A2 (pt) sistemas e métodos de controle adequados para utilização com sistemas e métodos de produção de energia
AR100543A1 (es) Mejora del desempeño de levantamiento de pozos
BR112017006733A2 (pt) método para determinar um design de lente de uma lente óptica adaptado a um usuário
TR201819419T4 (tr) Yeni tetrahidropiridopirimidin bileşiği veya tuzu.
BR112017017071A2 (pt) nova lisina descarboxilase, e método para produzir cadaverina utilizando a mesma
BR112016025443A2 (pt) sulfatos de heparano
BR112016011899A2 (pt) Processo para preparação de 5-fluoro-1h-pirazóis
BR112017013286A2 (pt) composto de isoxazolina, e, uso de um composto de isoxazolina.
BR112018003434A2 (pt) método para aperfeiçoamento de desempenho de um modelo de aprendizagem de máquina treinado
BR112017014772A2 (pt) reator de turbo-hélice com alimentação
BR112016018162A2 (pt) microrganismo modificado, método para produzir um composto orgânico e uso de um microrganismo
TWD175782S (zh) 緩衝器
TWD188654S (zh) 巴士

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]
B09A Decision: intention to grant [chapter 9.1 patent gazette]
B09W Correction of the decision to grant [chapter 9.1.4 patent gazette]

Free format text: O PRESENTE PEDIDO TEVE UM PARECER DE DEFERIMENTO NOTIFICADO NA RPI 2748 DE 05/09/2023, TENDO SIDO CONSTATADO INCORRECOES NAS INDICACOES DOS DOCUMENTOS QUE DEVEM COMPOR A CARTA-PATENTE, MAIS ESPECIFICAMENTE COM RELACAO A PAGINACAO DOS DESENHOS. ASSIM, RETIFICA-SE O DEFERIMENTO DO PEDIDO.

B16A Patent or certificate of addition of invention granted [chapter 16.1 patent gazette]

Free format text: PRAZO DE VALIDADE: 20 (VINTE) ANOS CONTADOS A PARTIR DE 11/08/2016, OBSERVADAS AS CONDICOES LEGAIS