| http://dbpedia.org/ontology/abstract
|
A rede bayesiana é uma ferramenta de model … A rede bayesiana é uma ferramenta de modelagem para atribuir probabilidades a eventos e, assim, caracterizar a incerteza nas previsões de um modelo. Aprendizagem profunda e redes neurais artificiais são abordagens usadas no aprendizado de máquina para construir modelos computacionais que aprendam com exemplos de treinamento. As redes neurais bayesianas mesclam esses campos. Elas são um tipo de Rede neural artificial cujos parâmetros e previsões são probabilísticos. Enquanto as redes neurais artificiais padrão geralmente atribuem alta confiança até mesmo para previsões incorretas, as redes neurais bayesianas podem avaliar com mais precisão a probabilidade de suas previsões estarem corretas. As Redes Neurais de Processo Gaussiano (RNPGs) são equivalentes às redes neurais Bayesianas até um determinado limite, e fornecem uma forma fechada de avaliar redes neurais bayesianas. Elas são uma distribuição de probabilidade do processo gaussiano que descreve a distribuição sobre as previsões feitas pela rede neural bayesiana correspondente. A computação em redes neurais artificiais é geralmente organizada em camadas sequenciais de neurônios artificiais. O número de neurônios em uma camada é chamado de largura da camada. A equivalência entre RNPGs e redes neurais bayesianas ocorre quando as camadas em uma rede neural bayesiana se tornam infinitamente largas (veja a figura). Este grande limite de largura é de interesse prático, uma vez que as redes neurais de largura finita normalmente funcionam estritamente melhor à medida que a largura da camada é aumentada.edida que a largura da camada é aumentada.
, Bayesian networks are a modeling tool for … Bayesian networks are a modeling tool for assigning probabilities to events, and thereby characterizing the uncertainty in a model's predictions. Deep learning and artificial neural networks are approaches used in machine learning to build computational models which learn from training examples. Bayesian neural networks merge these fields. They are a type of artificial neural network whose parameters and predictions are both probabilistic. While standard artificial neural networks often assign high confidence even to incorrect predictions, Bayesian neural networks can more accurately evaluate how likely their predictions are to be correct. Neural Network Gaussian Processes (NNGPs) are equivalent to Bayesian neural networks in a particular limit, and provide a closed form way to evaluate Bayesian neural networks. They are a Gaussian process probability distribution which describes the distribution over predictions made by the corresponding Bayesian neural network. Computation in artificial neural networks is usually organized into sequential layers of artificial neurons. The number of neurons in a layer is called the layer width. The equivalence between NNGPs and Bayesian neural networks occurs when the layers in a Bayesian neural network become infinitely wide (see figure). This large width limit is of practical interest, since finite width neural networks typically perform strictly better as layer width is increased. The NNGP also appears in several other contexts: it describes the distribution over predictions made by wide non-Bayesian artificial neural networks after random initialization of their parameters, but before training; it appears as a term in neural tangent kernel prediction equations; it is used in to characterize whether hyperparameters and architectures will be trainable. It is related to other large width limits of neural networks.her large width limits of neural networks.
|
| http://dbpedia.org/ontology/thumbnail
|
http://commons.wikimedia.org/wiki/Special:FilePath/Wide_neural_networks_are_described_by_a_Gaussian_process_svg.svg?width=300 +
|
| http://dbpedia.org/ontology/wikiPageExternalLink
|
https://github.com/google/neural-tangents +
|
| http://dbpedia.org/ontology/wikiPageID
|
63513679
|
| http://dbpedia.org/ontology/wikiPageLength
|
20714
|
| http://dbpedia.org/ontology/wikiPageRevisionID
|
1077703300
|
| http://dbpedia.org/ontology/wikiPageWikiLink
|
http://dbpedia.org/resource/Large_width_limits_of_neural_networks +
, http://dbpedia.org/resource/Python_%28programming_language%29 +
, http://dbpedia.org/resource/Error_function +
, http://dbpedia.org/resource/Artificial_neuron +
, http://dbpedia.org/resource/Probability_distribution +
, http://dbpedia.org/resource/Tensor_program +
, http://dbpedia.org/resource/Free_and_open-source +
, http://dbpedia.org/resource/Deep_information_propagation +
, http://dbpedia.org/resource/Gaussian_process +
, http://dbpedia.org/resource/File:Infinitely_wide_neural_network.webm +
, http://dbpedia.org/resource/Batch_normalization +
, http://dbpedia.org/resource/File:Wide_neural_networks_are_described_by_a_Gaussian_process_svg.svg +
, http://dbpedia.org/resource/Category:Bayesian_statistics +
, http://dbpedia.org/resource/File:Fully_connected_architecture.pdf +
, http://dbpedia.org/resource/Category:Artificial_neural_networks +
, http://dbpedia.org/resource/Category:Bayesian_networks +
, http://dbpedia.org/resource/Recurrent_neural_network +
, http://dbpedia.org/resource/Category:Kernel_methods_for_machine_learning +
, http://dbpedia.org/resource/Bayesian_network +
, http://dbpedia.org/resource/Artificial_neural_network +
, http://dbpedia.org/resource/Rectifier_%28neural_networks%29 +
, http://dbpedia.org/resource/Machine_learning +
, http://dbpedia.org/resource/Category:Machine_learning +
, http://dbpedia.org/resource/Deep_learning +
, http://dbpedia.org/resource/Convolutional_neural_network +
, http://dbpedia.org/resource/Neural_tangent_kernel +
, http://dbpedia.org/resource/Statistical_parameter +
, http://dbpedia.org/resource/LSTM +
, http://dbpedia.org/resource/Fully_connected_network +
, http://dbpedia.org/resource/Closed-form_expression +
, http://dbpedia.org/resource/Category:Deep_learning +
, http://dbpedia.org/resource/Gated_recurrent_unit +
|
| http://dbpedia.org/property/wikiPageUsesTemplate
|
http://dbpedia.org/resource/Template:Reflist +
|
| http://purl.org/dc/terms/subject
|
http://dbpedia.org/resource/Category:Artificial_neural_networks +
, http://dbpedia.org/resource/Category:Bayesian_networks +
, http://dbpedia.org/resource/Category:Deep_learning +
, http://dbpedia.org/resource/Category:Machine_learning +
, http://dbpedia.org/resource/Category:Bayesian_statistics +
, http://dbpedia.org/resource/Category:Kernel_methods_for_machine_learning +
|
| http://www.w3.org/ns/prov#wasDerivedFrom
|
http://en.wikipedia.org/wiki/Neural_network_Gaussian_process?oldid=1077703300&ns=0 +
|
| http://xmlns.com/foaf/0.1/depiction
|
http://commons.wikimedia.org/wiki/Special:FilePath/Wide_neural_networks_are_described_by_a_Gaussian_process_svg.svg +
|
| http://xmlns.com/foaf/0.1/isPrimaryTopicOf
|
http://en.wikipedia.org/wiki/Neural_network_Gaussian_process +
|
| owl:sameAs |
http://fa.dbpedia.org/resource/%D9%81%D8%B1%D8%A2%DB%8C%D9%86%D8%AF_%DA%AF%D8%A7%D9%88%D8%B3%DB%8C_%D8%B4%D8%A8%DA%A9%D9%87_%D8%B9%D8%B5%D8%A8%DB%8C +
, http://pt.dbpedia.org/resource/Rede_neural_de_processo_Gaussiano +
, https://global.dbpedia.org/id/C1ib9 +
, http://www.wikidata.org/entity/Q96395262 +
, http://dbpedia.org/resource/Neural_network_Gaussian_process +
|
| rdfs:comment |
A rede bayesiana é uma ferramenta de model … A rede bayesiana é uma ferramenta de modelagem para atribuir probabilidades a eventos e, assim, caracterizar a incerteza nas previsões de um modelo. Aprendizagem profunda e redes neurais artificiais são abordagens usadas no aprendizado de máquina para construir modelos computacionais que aprendam com exemplos de treinamento. As redes neurais bayesianas mesclam esses campos. Elas são um tipo de Rede neural artificial cujos parâmetros e previsões são probabilísticos. Enquanto as redes neurais artificiais padrão geralmente atribuem alta confiança até mesmo para previsões incorretas, as redes neurais bayesianas podem avaliar com mais precisão a probabilidade de suas previsões estarem corretas.lidade de suas previsões estarem corretas.
, Bayesian networks are a modeling tool for … Bayesian networks are a modeling tool for assigning probabilities to events, and thereby characterizing the uncertainty in a model's predictions. Deep learning and artificial neural networks are approaches used in machine learning to build computational models which learn from training examples. Bayesian neural networks merge these fields. They are a type of artificial neural network whose parameters and predictions are both probabilistic. While standard artificial neural networks often assign high confidence even to incorrect predictions, Bayesian neural networks can more accurately evaluate how likely their predictions are to be correct.ikely their predictions are to be correct.
|
| rdfs:label |
Neural network Gaussian process
, Rede neural de processo Gaussiano
|
