Matches in SemOpenAlex for { <https://semopenalex.org/work/W2742485803> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2742485803 abstract "In this talk, I'd like to discuss the intertwining importance and connections of three principles of data science in the title in data-driven decisions. Making prediction as its central task and embracing computation as its core, machine learning has enabled wide-ranging data-driven successes. Prediction is a useful way to check with reality. Good prediction implicitly assumes stability between past and future. Stability (relative to data and model perturbations) is also a minimum requirement for interpretability and reproducibility of data driven results (cf. Yu, 2013). It is closely related to uncertainty assessment. Obviously, both prediction and stability principles can not be employed without feasible computational algorithms, hence the importance of computability. The three principles will be demonstrated in the context of two neuroscience projects and through analytical connections. In particular, the first project adds stability to predictive modeling used for reconstruction of movies from fMRI brain signlas for interpretable models. The second project use predictive transfer learning that combines AlexNet, GoogleNet and VGG with single V4 neuron data for state-of-the-art prediction performance. Our results lend support, to a certain extent, to the resemblance of these CNNs to brain and at the same time provide stable pattern interpretations of neurons in the difficult primate visual cortex V4." @default.
- W2742485803 created "2017-08-17" @default.
- W2742485803 creator A5015318204 @default.
- W2742485803 date "2017-08-04" @default.
- W2742485803 modified "2023-09-25" @default.
- W2742485803 title "Three Principles of Data Science" @default.
- W2742485803 doi "https://doi.org/10.1145/3097983.3105808" @default.
- W2742485803 hasPublicationYear "2017" @default.
- W2742485803 type Work @default.
- W2742485803 sameAs 2742485803 @default.
- W2742485803 citedByCount "3" @default.
- W2742485803 countsByYear W27424858032017 @default.
- W2742485803 countsByYear W27424858032021 @default.
- W2742485803 countsByYear W27424858032022 @default.
- W2742485803 crossrefType "proceedings-article" @default.
- W2742485803 hasAuthorship W2742485803A5015318204 @default.
- W2742485803 hasConcept C105795698 @default.
- W2742485803 hasConcept C112972136 @default.
- W2742485803 hasConcept C119857082 @default.
- W2742485803 hasConcept C151730666 @default.
- W2742485803 hasConcept C152062344 @default.
- W2742485803 hasConcept C154945302 @default.
- W2742485803 hasConcept C162324750 @default.
- W2742485803 hasConcept C187736073 @default.
- W2742485803 hasConcept C197640229 @default.
- W2742485803 hasConcept C2779343474 @default.
- W2742485803 hasConcept C2780451532 @default.
- W2742485803 hasConcept C2781067378 @default.
- W2742485803 hasConcept C33923547 @default.
- W2742485803 hasConcept C41008148 @default.
- W2742485803 hasConcept C80444323 @default.
- W2742485803 hasConcept C86803240 @default.
- W2742485803 hasConceptScore W2742485803C105795698 @default.
- W2742485803 hasConceptScore W2742485803C112972136 @default.
- W2742485803 hasConceptScore W2742485803C119857082 @default.
- W2742485803 hasConceptScore W2742485803C151730666 @default.
- W2742485803 hasConceptScore W2742485803C152062344 @default.
- W2742485803 hasConceptScore W2742485803C154945302 @default.
- W2742485803 hasConceptScore W2742485803C162324750 @default.
- W2742485803 hasConceptScore W2742485803C187736073 @default.
- W2742485803 hasConceptScore W2742485803C197640229 @default.
- W2742485803 hasConceptScore W2742485803C2779343474 @default.
- W2742485803 hasConceptScore W2742485803C2780451532 @default.
- W2742485803 hasConceptScore W2742485803C2781067378 @default.
- W2742485803 hasConceptScore W2742485803C33923547 @default.
- W2742485803 hasConceptScore W2742485803C41008148 @default.
- W2742485803 hasConceptScore W2742485803C80444323 @default.
- W2742485803 hasConceptScore W2742485803C86803240 @default.
- W2742485803 hasLocation W27424858031 @default.
- W2742485803 hasOpenAccess W2742485803 @default.
- W2742485803 hasPrimaryLocation W27424858031 @default.
- W2742485803 hasRelatedWork W156562335 @default.
- W2742485803 hasRelatedWork W2068398673 @default.
- W2742485803 hasRelatedWork W2090302955 @default.
- W2742485803 hasRelatedWork W2549603914 @default.
- W2742485803 hasRelatedWork W2618851150 @default.
- W2742485803 hasRelatedWork W2736796149 @default.
- W2742485803 hasRelatedWork W2777412843 @default.
- W2742485803 hasRelatedWork W2810939025 @default.
- W2742485803 hasRelatedWork W2951885001 @default.
- W2742485803 hasRelatedWork W2962927818 @default.
- W2742485803 hasRelatedWork W3003747211 @default.
- W2742485803 hasRelatedWork W3015817736 @default.
- W2742485803 hasRelatedWork W3037319882 @default.
- W2742485803 hasRelatedWork W3081974308 @default.
- W2742485803 hasRelatedWork W3083127930 @default.
- W2742485803 hasRelatedWork W3097521164 @default.
- W2742485803 hasRelatedWork W3161201512 @default.
- W2742485803 hasRelatedWork W3169604521 @default.
- W2742485803 hasRelatedWork W3183124339 @default.
- W2742485803 hasRelatedWork W3184764835 @default.
- W2742485803 isParatext "false" @default.
- W2742485803 isRetracted "false" @default.
- W2742485803 magId "2742485803" @default.
- W2742485803 workType "article" @default.