Matches in SemOpenAlex for { <https://semopenalex.org/work/W1930673955> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W1930673955 abstract "Generalisation is a non-trivial problem in machine learning and more so with neural networks which have the capabilities of inducing varying degrees of freedom. It is influenced by many factors in network design, such as network size, initial conditions, learning rate, weight decay factor, pruning algorithms, and many more. In spite of continuous research efforts, we could not arrive at a practical solution which can offer a superior generalisation. We present a novel approach for handling complex problems of machine learning. A multiobjective genetic algorithm is used for identifying (near-) optimal subspaces for hierarchical learning. This strategy of explicitly partitioning the data for subsequent mapping onto a hierarchical classifier is found both to reduce the learning complexity and the classification time. The classification performance of various algorithms is compared and it is argued that the neural modules are superior for learning the localised decision surfaces of such partitions and offer better generalisation." @default.
- W1930673955 created "2016-06-24" @default.
- W1930673955 creator A5031751695 @default.
- W1930673955 date "2003-01-20" @default.
- W1930673955 modified "2023-09-24" @default.
- W1930673955 title "On generalisation of machine learning with neural-evolutionary computations" @default.
- W1930673955 cites W2025653905 @default.
- W1930673955 cites W2076118331 @default.
- W1930673955 cites W2099689253 @default.
- W1930673955 cites W2145085734 @default.
- W1930673955 cites W2151554678 @default.
- W1930673955 doi "https://doi.org/10.1109/iccima.1999.798512" @default.
- W1930673955 hasPublicationYear "2003" @default.
- W1930673955 type Work @default.
- W1930673955 sameAs 1930673955 @default.
- W1930673955 citedByCount "1" @default.
- W1930673955 countsByYear W19306739552012 @default.
- W1930673955 crossrefType "proceedings-article" @default.
- W1930673955 hasAuthorship W1930673955A5031751695 @default.
- W1930673955 hasConcept C105902424 @default.
- W1930673955 hasConcept C108010975 @default.
- W1930673955 hasConcept C11413529 @default.
- W1930673955 hasConcept C119857082 @default.
- W1930673955 hasConcept C154945302 @default.
- W1930673955 hasConcept C41008148 @default.
- W1930673955 hasConcept C45374587 @default.
- W1930673955 hasConcept C50644808 @default.
- W1930673955 hasConcept C6557445 @default.
- W1930673955 hasConcept C86803240 @default.
- W1930673955 hasConcept C95623464 @default.
- W1930673955 hasConceptScore W1930673955C105902424 @default.
- W1930673955 hasConceptScore W1930673955C108010975 @default.
- W1930673955 hasConceptScore W1930673955C11413529 @default.
- W1930673955 hasConceptScore W1930673955C119857082 @default.
- W1930673955 hasConceptScore W1930673955C154945302 @default.
- W1930673955 hasConceptScore W1930673955C41008148 @default.
- W1930673955 hasConceptScore W1930673955C45374587 @default.
- W1930673955 hasConceptScore W1930673955C50644808 @default.
- W1930673955 hasConceptScore W1930673955C6557445 @default.
- W1930673955 hasConceptScore W1930673955C86803240 @default.
- W1930673955 hasConceptScore W1930673955C95623464 @default.
- W1930673955 hasLocation W19306739551 @default.
- W1930673955 hasOpenAccess W1930673955 @default.
- W1930673955 hasPrimaryLocation W19306739551 @default.
- W1930673955 hasRelatedWork W1563716968 @default.
- W1930673955 hasRelatedWork W1758923908 @default.
- W1930673955 hasRelatedWork W1966454050 @default.
- W1930673955 hasRelatedWork W1991012117 @default.
- W1930673955 hasRelatedWork W2026229593 @default.
- W1930673955 hasRelatedWork W2068448068 @default.
- W1930673955 hasRelatedWork W2110179049 @default.
- W1930673955 hasRelatedWork W2111101775 @default.
- W1930673955 hasRelatedWork W2114173890 @default.
- W1930673955 hasRelatedWork W2122744052 @default.
- W1930673955 hasRelatedWork W2137762954 @default.
- W1930673955 hasRelatedWork W2148511931 @default.
- W1930673955 hasRelatedWork W2161519575 @default.
- W1930673955 hasRelatedWork W2165934307 @default.
- W1930673955 hasRelatedWork W2338592249 @default.
- W1930673955 hasRelatedWork W2481392060 @default.
- W1930673955 hasRelatedWork W2607462057 @default.
- W1930673955 hasRelatedWork W2765611817 @default.
- W1930673955 hasRelatedWork W95342718 @default.
- W1930673955 hasRelatedWork W99131004 @default.
- W1930673955 isParatext "false" @default.
- W1930673955 isRetracted "false" @default.
- W1930673955 magId "1930673955" @default.
- W1930673955 workType "article" @default.