Matches in SemOpenAlex for { <https://semopenalex.org/work/W2754120167> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2754120167 abstract "This dissertation models natural image and language data with data-driven methods with focus in the interpretation of the emergent representation. Cognitive development and processing learns to handle input from the surrounding environment. Similarly, data-driven methods offer a flexible way to find exploratory views of the data.Independent Component Analysis (ICA) is a proven unsupervised method especially in the field of neural signal processing. It can extract cognitively relevant source signals from seemingly garbled signal mixtures with the assumption of statistical independence. The concept is closely related to sparse coding, which is neurobiologically efficient and is a view of how sensory information is processed in the brain.In the analysis of small video segments, another statistical concept, temporal coherence, is applied and the results are compared to those of ICA. The representations learned share major characteristics with those measured from the early processing in the visual cortex. A unified model which combines sparseness, temporal coherence and topological organization is introduced.With similar methodological tools, the focus is shifted to natural language data with only minimal preprocessing in order to create language-independent methods. The meaning of words can be modeled with contextual co-occurrence information collected from a large corpus and vector space models. In contrast to classical methods utilizing second-order statistics, the ICA method can reveal the underlying sparse structure and make the representation more interpretable. In addition to validating the applied unsupervised methodology, the experimental results indicate that the parametrization of the data has a very large effect on the representation learned. With the developed analysis tools, the structure learned is matched to syntactic and semantic features at different levels. For translated sentence pairs, the result is a multilingual representation for words. The increased sparsity of the representations learned is validated by further nonlinear thresholding. The findings can be utilized to build distributional models for words which match better with semantic theories of word classes and relationships among word meanings in natural language processing tasks where more interpretability is desired.; Tassa vaitoskirjassa mallinnetaan aineistolahteisesti luonnollisia kuvia ja tekstia seka tarkastellaan niista loydettyja esitystapoja. Ymparistosta tulevat arsykkeet ohjaavat kognitiivista kehitysta ja aivojen toimintaa. Aineistolahtoiset laskennalliset menetelmat tarjoavat vastaavasti joustavan tavan loytaa erilaisia eksploratiivisia nakokulmia.Riippumattomien komponenttien analyysi (ICA) on ansioitunut ohjaamaton tilastollinen menetelma erityisesti hermostollisten vasteiden kasittelyssa. Se pystyy erottamaan kognitiivisesti olennaiset lahteet naennaisesti sekoittuneista signaaleista tilastollisen riippumattomuusoletuksen avulla. Tama konsepti liittyy laheisesti harvakoodaukseen, joka on neurobiologisesti tehokas ja…" @default.
- W2754120167 created "2017-09-25" @default.
- W2754120167 creator A5050352884 @default.
- W2754120167 date "2017-01-01" @default.
- W2754120167 modified "2023-09-26" @default.
- W2754120167 title "Emergence of representations in natural data" @default.
- W2754120167 hasPublicationYear "2017" @default.
- W2754120167 type Work @default.
- W2754120167 sameAs 2754120167 @default.
- W2754120167 citedByCount "0" @default.
- W2754120167 crossrefType "journal-article" @default.
- W2754120167 hasAuthorship W2754120167A5050352884 @default.
- W2754120167 hasConcept C105795698 @default.
- W2754120167 hasConcept C119857082 @default.
- W2754120167 hasConcept C120665830 @default.
- W2754120167 hasConcept C121332964 @default.
- W2754120167 hasConcept C153180895 @default.
- W2754120167 hasConcept C154945302 @default.
- W2754120167 hasConcept C17744445 @default.
- W2754120167 hasConcept C192209626 @default.
- W2754120167 hasConcept C199539241 @default.
- W2754120167 hasConcept C204321447 @default.
- W2754120167 hasConcept C2776359362 @default.
- W2754120167 hasConcept C2781181686 @default.
- W2754120167 hasConcept C33923547 @default.
- W2754120167 hasConcept C34736171 @default.
- W2754120167 hasConcept C41008148 @default.
- W2754120167 hasConcept C51432778 @default.
- W2754120167 hasConcept C77637269 @default.
- W2754120167 hasConcept C94625758 @default.
- W2754120167 hasConceptScore W2754120167C105795698 @default.
- W2754120167 hasConceptScore W2754120167C119857082 @default.
- W2754120167 hasConceptScore W2754120167C120665830 @default.
- W2754120167 hasConceptScore W2754120167C121332964 @default.
- W2754120167 hasConceptScore W2754120167C153180895 @default.
- W2754120167 hasConceptScore W2754120167C154945302 @default.
- W2754120167 hasConceptScore W2754120167C17744445 @default.
- W2754120167 hasConceptScore W2754120167C192209626 @default.
- W2754120167 hasConceptScore W2754120167C199539241 @default.
- W2754120167 hasConceptScore W2754120167C204321447 @default.
- W2754120167 hasConceptScore W2754120167C2776359362 @default.
- W2754120167 hasConceptScore W2754120167C2781181686 @default.
- W2754120167 hasConceptScore W2754120167C33923547 @default.
- W2754120167 hasConceptScore W2754120167C34736171 @default.
- W2754120167 hasConceptScore W2754120167C41008148 @default.
- W2754120167 hasConceptScore W2754120167C51432778 @default.
- W2754120167 hasConceptScore W2754120167C77637269 @default.
- W2754120167 hasConceptScore W2754120167C94625758 @default.
- W2754120167 hasLocation W27541201671 @default.
- W2754120167 hasOpenAccess W2754120167 @default.
- W2754120167 hasPrimaryLocation W27541201671 @default.
- W2754120167 hasRelatedWork W1562955078 @default.
- W2754120167 hasRelatedWork W2091558631 @default.
- W2754120167 hasRelatedWork W2251041941 @default.
- W2754120167 hasRelatedWork W2467343197 @default.
- W2754120167 hasRelatedWork W2890225654 @default.
- W2754120167 hasRelatedWork W2892282605 @default.
- W2754120167 hasRelatedWork W2896220889 @default.
- W2754120167 hasRelatedWork W2920732287 @default.
- W2754120167 hasRelatedWork W2942688450 @default.
- W2754120167 hasRelatedWork W2951585248 @default.
- W2754120167 hasRelatedWork W2973992035 @default.
- W2754120167 hasRelatedWork W2987352513 @default.
- W2754120167 hasRelatedWork W2990370999 @default.
- W2754120167 hasRelatedWork W3022408116 @default.
- W2754120167 hasRelatedWork W3081761753 @default.
- W2754120167 hasRelatedWork W3102226577 @default.
- W2754120167 hasRelatedWork W3113032096 @default.
- W2754120167 hasRelatedWork W3165244476 @default.
- W2754120167 hasRelatedWork W3170192073 @default.
- W2754120167 hasRelatedWork W3185952614 @default.
- W2754120167 isParatext "false" @default.
- W2754120167 isRetracted "false" @default.
- W2754120167 magId "2754120167" @default.
- W2754120167 workType "article" @default.