FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208636224> ?p ?o ?g. }

• W3208636224 abstract "Merging the two cultures of deep and statistical learning provides insights into structured high-dimensional data. Traditional statistical modeling is still a dominant strategy for structured tabular data. Deep learning can be viewed through the lens of generalized linear models (GLMs) with composite link functions. Sufficient dimensionality reduction (SDR) and sparsity performs nonlinear feature engineering. We show that prediction, interpolation and uncertainty quantification can be achieved using probabilistic methods at the output layer of the model. Thus a general framework for machine learning arises that first generates nonlinear features (a.k.a factors) via sparse regularization and stochastic gradient optimisation and second uses a stochastic output layer for predictive uncertainty. Rather than using shallow additive architectures as in many statistical models, deep learning uses layers of semi affine input transformations to provide a predictive rule. Applying these layers of transformations leads to a set of attributes (a.k.a features) to which predictive statistical methods can be applied. Thus we achieve the best of both worlds: scalability and fast predictive rule construction together with uncertainty quantification. Sparse regularisation with un-supervised or supervised learning finds the features. We clarify the duality between shallow and wide models such as PCA, PPR, RRR and deep but skinny architectures such as autoencoders, MLPs, CNN, and LSTM. The connection with data transformations is of practical importance for finding good network architectures. By incorporating probabilistic components at the output level we allow for predictive uncertainty. For interpolation we use deep Gaussian process and ReLU trees for classification. We provide applications to regression, classification and interpolation. Finally, we conclude with directions for future research." @default.
• W3208636224 created "2021-11-08" @default.
• W3208636224 creator A5012467860 @default.
• W3208636224 creator A5020522149 @default.
• W3208636224 creator A5032033428 @default.
• W3208636224 creator A5081284665 @default.
• W3208636224 creator A5086643947 @default.
• W3208636224 date "2021-10-21" @default.
• W3208636224 modified "2023-09-26" @default.
• W3208636224 title "Merging Two Cultures: Deep and Statistical Learning" @default.
• W3208636224 cites W1506069954 @default.
• W3208636224 cites W1528905581 @default.
• W3208636224 cites W1554663460 @default.
• W3208636224 cites W1923906081 @default.
• W3208636224 cites W1979612645 @default.
• W3208636224 cites W1999663487 @default.
• W3208636224 cites W2022215192 @default.
• W3208636224 cites W2072128103 @default.
• W3208636224 cites W2072442004 @default.
• W3208636224 cites W2080006911 @default.
• W3208636224 cites W2081566336 @default.
• W3208636224 cites W2084341220 @default.
• W3208636224 cites W2084840427 @default.
• W3208636224 cites W2092271904 @default.
• W3208636224 cites W2095705004 @default.
• W3208636224 cites W2099878672 @default.
• W3208636224 cites W2101837070 @default.
• W3208636224 cites W2115305054 @default.
• W3208636224 cites W2117812871 @default.
• W3208636224 cites W2120240539 @default.
• W3208636224 cites W2137225583 @default.
• W3208636224 cites W2145889472 @default.
• W3208636224 cites W2160333357 @default.
• W3208636224 cites W2163490846 @default.
• W3208636224 cites W2166446427 @default.
• W3208636224 cites W2171618211 @default.
• W3208636224 cites W2248214328 @default.
• W3208636224 cites W2304999498 @default.
• W3208636224 cites W2479236352 @default.
• W3208636224 cites W2502852798 @default.
• W3208636224 cites W2511106335 @default.
• W3208636224 cites W2514303448 @default.
• W3208636224 cites W2586702902 @default.
• W3208636224 cites W2592929672 @default.
• W3208636224 cites W2613296909 @default.
• W3208636224 cites W2620965429 @default.
• W3208636224 cites W2698898 @default.
• W3208636224 cites W2794607344 @default.
• W3208636224 cites W2798909945 @default.
• W3208636224 cites W2941442828 @default.
• W3208636224 cites W2963341956 @default.
• W3208636224 cites W2963433767 @default.
• W3208636224 cites W2963698230 @default.
• W3208636224 cites W2975408209 @default.
• W3208636224 cites W2978269572 @default.
• W3208636224 cites W2997829126 @default.
• W3208636224 cites W3174220711 @default.
• W3208636224 cites W14377099 @default.
• W3208636224 doi "https://doi.org/10.48550/arxiv.2110.11561" @default.
• W3208636224 hasPublicationYear "2021" @default.
• W3208636224 type Work @default.
• W3208636224 sameAs 3208636224 @default.
• W3208636224 citedByCount "0" @default.
• W3208636224 crossrefType "posted-content" @default.
• W3208636224 hasAuthorship W3208636224A5012467860 @default.
• W3208636224 hasAuthorship W3208636224A5020522149 @default.
• W3208636224 hasAuthorship W3208636224A5032033428 @default.
• W3208636224 hasAuthorship W3208636224A5081284665 @default.
• W3208636224 hasAuthorship W3208636224A5086643947 @default.
• W3208636224 hasBestOaLocation W32086362241 @default.
• W3208636224 hasConcept C108583219 @default.
• W3208636224 hasConcept C11413529 @default.
• W3208636224 hasConcept C114289077 @default.
• W3208636224 hasConcept C119857082 @default.
• W3208636224 hasConcept C121332964 @default.
• W3208636224 hasConcept C154945302 @default.
• W3208636224 hasConcept C163716315 @default.
• W3208636224 hasConcept C206688291 @default.
• W3208636224 hasConcept C2776135515 @default.
• W3208636224 hasConcept C2778827112 @default.
• W3208636224 hasConcept C41008148 @default.
• W3208636224 hasConcept C48044578 @default.
• W3208636224 hasConcept C49937458 @default.
• W3208636224 hasConcept C50644808 @default.
• W3208636224 hasConcept C61326573 @default.
• W3208636224 hasConcept C62520636 @default.
• W3208636224 hasConcept C70518039 @default.
• W3208636224 hasConcept C77088390 @default.
• W3208636224 hasConcept C97385483 @default.
• W3208636224 hasConceptScore W3208636224C108583219 @default.
• W3208636224 hasConceptScore W3208636224C11413529 @default.
• W3208636224 hasConceptScore W3208636224C114289077 @default.
• W3208636224 hasConceptScore W3208636224C119857082 @default.
• W3208636224 hasConceptScore W3208636224C121332964 @default.
• W3208636224 hasConceptScore W3208636224C154945302 @default.
• W3208636224 hasConceptScore W3208636224C163716315 @default.
• W3208636224 hasConceptScore W3208636224C206688291 @default.
• W3208636224 hasConceptScore W3208636224C2776135515 @default.
• W3208636224 hasConceptScore W3208636224C2778827112 @default.
• W3208636224 hasConceptScore W3208636224C41008148 @default.

• next