FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2473005013> ?p ?o ?g. }

• W2473005013 abstract "Neural networks are widely used for nonlinear pattern recognition and regression. However, they are considered as black boxes due to lack of transparency of internal workings and lack of direct relevance of its structure to the problem being addressed making it difficult to gain insights. Furthermore, structure of a neural network requires optimization which is still a challenge. Many existing structure optimization approaches require either extensive multi-stage pruning or setting subjective thresholds for pruning parameters. The knowledge of any internal consistency in the behavior of neurons could help develop simpler, systematic and more efficient approaches to optimise network structure. This chapter addresses in detail the issue of internal consistency in relation to redundancy and robustness of network structure of feed forward networks (3-layer) that are widely used for nonlinear regression. It first investigates if there is a recognizable consistency in neuron activation patterns under all conditions of network operation such as noise and initial weights. If such consistency exists, it points to a recognizable optimum network structure for given data. The results show that such pattern does exist and it is most clearly evident not at the level of hidden neuron activation but hidden neuron input to the output neuron (i.e., weighted hidden neuron activation). It is shown that when a network has more than the optimum number of hidden neurons, the redundant neurons form clearly distinguishable correlated patterns of their weighted outputs. This correlation structure is exploited to extract the required number of neurons using correlation distance based self organising maps that are clustered using Ward clustering that optimally cluster correlated weighted hidden neuron activity patterns without any user defined criteria or thresholds, thus automatically optimizing network structure in one step. The number of Ward clusters on the SOM is the required optimum number of neurons. The SOM/Ward based optimum network is compared with that obtained using two documented pruning methods: optimal brain damage and variance nullity measure to show the efficacy of the correlation approach in providing equivalent results. Also, the robustness of the network with optimum structure is tested against perturbation of weights and confidence intervals for weights are illustrated. Finally, the approach is tested on two practical problems involving a breast cancer diagnostic system and river flow forecasting." @default.
• W2473005013 created "2016-07-22" @default.
• W2473005013 creator A5091682385 @default.
• W2473005013 date "2016-01-01" @default.
• W2473005013 modified "2023-09-27" @default.
• W2473005013 title "Order in the Black Box: Consistency and Robustness of Hidden Neuron Activation of Feed Forward Neural Networks and Its Use in Efficient Optimization of Network Structure" @default.
• W2473005013 cites W1532221965 @default.
• W2473005013 cites W1994723463 @default.
• W2473005013 cites W2014751046 @default.
• W2473005013 cites W2016381774 @default.
• W2473005013 cites W2023793984 @default.
• W2473005013 cites W2026495637 @default.
• W2473005013 cites W2027197837 @default.
• W2473005013 cites W2039852947 @default.
• W2473005013 cites W2070665556 @default.
• W2473005013 cites W2088784721 @default.
• W2473005013 cites W2106721790 @default.
• W2473005013 cites W2109038936 @default.
• W2473005013 cites W2124290836 @default.
• W2473005013 cites W2145085734 @default.
• W2473005013 cites W2169228003 @default.
• W2473005013 cites W4246239324 @default.
• W2473005013 cites W2096013212 @default.
• W2473005013 doi "https://doi.org/10.1007/978-3-319-28495-8_2" @default.
• W2473005013 hasPublicationYear "2016" @default.
• W2473005013 type Work @default.
• W2473005013 sameAs 2473005013 @default.
• W2473005013 citedByCount "0" @default.
• W2473005013 crossrefType "book-chapter" @default.
• W2473005013 hasAuthorship W2473005013A5091682385 @default.
• W2473005013 hasConcept C104317684 @default.
• W2473005013 hasConcept C108010975 @default.
• W2473005013 hasConcept C153180895 @default.
• W2473005013 hasConcept C154945302 @default.
• W2473005013 hasConcept C185592680 @default.
• W2473005013 hasConcept C2776436953 @default.
• W2473005013 hasConcept C33923547 @default.
• W2473005013 hasConcept C41008148 @default.
• W2473005013 hasConcept C50644808 @default.
• W2473005013 hasConcept C55493867 @default.
• W2473005013 hasConcept C63479239 @default.
• W2473005013 hasConcept C6557445 @default.
• W2473005013 hasConcept C86803240 @default.
• W2473005013 hasConceptScore W2473005013C104317684 @default.
• W2473005013 hasConceptScore W2473005013C108010975 @default.
• W2473005013 hasConceptScore W2473005013C153180895 @default.
• W2473005013 hasConceptScore W2473005013C154945302 @default.
• W2473005013 hasConceptScore W2473005013C185592680 @default.
• W2473005013 hasConceptScore W2473005013C2776436953 @default.
• W2473005013 hasConceptScore W2473005013C33923547 @default.
• W2473005013 hasConceptScore W2473005013C41008148 @default.
• W2473005013 hasConceptScore W2473005013C50644808 @default.
• W2473005013 hasConceptScore W2473005013C55493867 @default.
• W2473005013 hasConceptScore W2473005013C63479239 @default.
• W2473005013 hasConceptScore W2473005013C6557445 @default.
• W2473005013 hasConceptScore W2473005013C86803240 @default.
• W2473005013 hasLocation W24730050131 @default.
• W2473005013 hasOpenAccess W2473005013 @default.
• W2473005013 hasPrimaryLocation W24730050131 @default.
• W2473005013 hasRelatedWork W191220328 @default.
• W2473005013 hasRelatedWork W1981984665 @default.
• W2473005013 hasRelatedWork W2041519358 @default.
• W2473005013 hasRelatedWork W2225087728 @default.
• W2473005013 hasRelatedWork W2312240384 @default.
• W2473005013 hasRelatedWork W2391996455 @default.
• W2473005013 hasRelatedWork W2392371707 @default.
• W2473005013 hasRelatedWork W2549252813 @default.
• W2473005013 hasRelatedWork W2621038397 @default.
• W2473005013 hasRelatedWork W264488922 @default.
• W2473005013 hasRelatedWork W2768551305 @default.
• W2473005013 hasRelatedWork W2791513483 @default.
• W2473005013 hasRelatedWork W2899753772 @default.
• W2473005013 hasRelatedWork W2945740093 @default.
• W2473005013 hasRelatedWork W2963145730 @default.
• W2473005013 hasRelatedWork W2990222711 @default.
• W2473005013 hasRelatedWork W3132115840 @default.
• W2473005013 hasRelatedWork W3134582530 @default.
• W2473005013 hasRelatedWork W3175388227 @default.
• W2473005013 hasRelatedWork W41733838 @default.
• W2473005013 isParatext "false" @default.
• W2473005013 isRetracted "false" @default.
• W2473005013 magId "2473005013" @default.
• W2473005013 workType "book-chapter" @default.