BR112018002248A2 - detecção de classes desconhecidas e inicialização de classificadores para classes desconhecidas - Google Patents

detecção de classes desconhecidas e inicialização de classificadores para classes desconhecidas

Info

Publication number
BR112018002248A2
BR112018002248A2 BR112018002248A BR112018002248A BR112018002248A2 BR 112018002248 A2 BR112018002248 A2 BR 112018002248A2 BR 112018002248 A BR112018002248 A BR 112018002248A BR 112018002248 A BR112018002248 A BR 112018002248A BR 112018002248 A2 BR112018002248 A2 BR 112018002248A2
Authority
BR
Brazil
Prior art keywords
unknown
classifier
classes
class detection
initialization
Prior art date
Application number
BR112018002248A
Other languages
English (en)
Other versions
BR112018002248B1 (pt
Inventor
Sarah Anthony
Lin Dexu
Blythe Towal Regan
Majumdar Somdeb
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 BR112018002248A2 publication Critical patent/BR112018002248A2/pt
Publication of BR112018002248B1 publication Critical patent/BR112018002248B1/pt

Links

Classifications

    • 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
    • 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
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield 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
    • G06N3/08—Learning methods
    • 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
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks

Landscapes

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

Abstract

um método de detecção de classes desconhecidas é apresentado e inclui a geração de um primeiro classificador para múltiplas primeiras classes. em uma configuração, uma saída do primeiro classificador tem uma dimensão de pelo menos dois. o método também inclui projetar um segundo classificador para receber a saída do primeiro classificador para decidir se os dados de entrada pertencem às múltiplas primeiras classes ou pelo menos uma segunda classe.
BR112018002248-9A 2015-08-04 2016-07-20 Detecção de classes desconhecidas e inicialização de classificadores para classes desconhecidas BR112018002248B1 (pt)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US201562201090P 2015-08-04 2015-08-04
US62/201,090 2015-08-04
US14/849,518 2015-09-09
US14/849,518 US20170039469A1 (en) 2015-08-04 2015-09-09 Detection of unknown classes and initialization of classifiers for unknown classes
PCT/US2016/043146 WO2017023551A2 (en) 2015-08-04 2016-07-20 Detection of unknown classes and initialization of classifiers for unknown classes

Publications (2)

Publication Number Publication Date
BR112018002248A2 true BR112018002248A2 (pt) 2018-09-18
BR112018002248B1 BR112018002248B1 (pt) 2023-05-30

Family

ID=

Also Published As

Publication number Publication date
EP3332362A2 (en) 2018-06-13
US20170039469A1 (en) 2017-02-09
JP6776331B2 (ja) 2020-10-28
KR20180037192A (ko) 2018-04-11
KR102595399B1 (ko) 2023-10-27
WO2017023551A2 (en) 2017-02-09
JP2018528525A (ja) 2018-09-27
WO2017023551A3 (en) 2017-04-13
CN107924491A (zh) 2018-04-17

Similar Documents

Publication Publication Date Title
WO2017023551A3 (en) Detection of unknown classes and initialization of classifiers for unknown classes
BR112018002040A2 (pt) controle de uma nuvem de dispositivo
BR112016023619A8 (pt) técnicas para otimização de potência com base em parâmetros de rede
BR112017003023A2 (pt) classificação enviesante de gráfico de conhecimento para dados
BR112018009596A2 (pt) sistema e método para determinar a saúde e o sexo de um pinto
BR112017014076A2 (pt) segurança para aplicativos móveis de pagamento.
PH12017501027B1 (en) Hidden node detection in lte licensed assisted access
WO2015123366A3 (en) Methods and apparatus to provide extended object notation data
AR101590A1 (es) Optimización de la utilización de recursos de hardware informático al procesar datos de precisión variables
BR112015023360A2 (pt) sistema e método de execução de hipervisores múltiplos
MX2022000580A (es) Sistemas, dispositivos, y metodos para detectar fertilidad y genero de huevos no eclosionados.
MX2016011921A (es) Configuracion de modo arquitectonico en un sistema de computo.
BR112015023894A2 (pt) sistema e método para determinação de propriedades de uma amostra
GB2559282A (en) Enhancing drilling operations with cognitive computing
BR112016007119A2 (pt) domínios de falha em hardware moderno
BR102013015147A8 (pt) método para a seleção de um algoritmo para uso em processamento de dados hiperespectrais
BR112015023219A2 (pt) sistema de desenho de objeto assistido por computador, meio não transitório de armazenamento legível em computador e método de fabrico de objeto
BR112017003426A2 (pt) fluxo de dados construído para processamento de evento intensificado
BR112017000852A2 (pt) ?aparelho e método para gerar um sinal melhorado utilizando enchimento de ruído independente?.
BR112017007442A2 (pt) roteamento de interrupção eficiente para um processador de várias threads
BR112018006393A2 (pt) método para classificar um linfoma difuso de grande célula b (dlbcl), uma ou mais mídias de armazenamento legíveis por computador, sistema de computação adaptado e kit
SG10201901587VA (en) Application testing
BR112016024813A2 (pt) processamento de meio tom de cor
BR112015027642A2 (pt) Classificador
BR112015026650A2 (pt) método para facilitar uma interface e aparelho

Legal Events

Date Code Title Description
B06U Preliminary requirement: requests with searches performed by other patent offices: procedure suspended [chapter 6.21 patent gazette]
B09A Decision: intention to grant [chapter 9.1 patent gazette]
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 20/07/2016, OBSERVADAS AS CONDICOES LEGAIS