Interpreting neural-network connection weights

Keywords

Connection (principal bundle), Artificial neural network, Computer science, Artificial intelligence, Mathematics

References

No references recorded for this paper.

Cited by

• Credit Scoring Based on Hybrid Data Mining ClassificationFeng-Chia Li, Pengkai Wang, Ying-Chieh Liu — 2009
• Some studies on the load carrying capacity of shallow foundation resting over geogrid-reinforced sand under eccentric loadRoma Sahu — 2013
• Prediction of CO maximum ground level concentrations in the Bay of Algeciras, Spain using artificial neural networks.Caroline Creamer, Neale Blair, Brendan O’Keeffe — 2008
• Artificial Neural Network for Total Laboratory Automation to Improve the Management of Sample DilutionNorimune Kawai — 2017
• Rainfall-Runoff Modelling Using Artificial Neural Networks (ANNs)Aman Mohammad Kalteh — 2007
• Comparison of Artificial Neural Network and Binary Logistic Regression for Classification of Chiropteran Dietary SpecializationsEric Adjei Lawer, Albert Luguterah, Suleman Nasiru — 2014
• Prediction of collapse potential via artificial neural networksGhassem Habibagahi, Mehdi Taherian — 2001
• Dead-end and crossflow microfiltration of yeast and bentonite suspensions: experimental and modelling studies incorporating the use of artificial neural networksJenny Ní Mhurchú — 2008
• Neural network decision support systems for the Department of Defense: an explorationMatthew Ludwig Laskowski — 1991
• Utilizing computational neural networks for evaluating the permeability of compacted clay linersYacoub M. Najjar, Imad A. Basheer — 1996
• An automated rule refinement systemRobert Andrews — 2003
• Connectionism Isn’t Just for Cognitive Science: Neural Networks as Methodological ToolsRobert McMillen, Tracy B. Henley — 2001
• Behaviour of eccentrically loaded shallow foundations on granular soilRupashree Ragini Sahoo — 2013
• A comparison of methods for assessing the relative importance of input variables in artificial neural networksHassan, Omar Maghawri Ibrahim — 2013
• Neural networks for inelastic distortional buckling capacity assessment of steel I-beamsSajjad Tohidi, Yasser Sharifi — 2015
• Parameter Sensitivity Analysis of Geotechnical Engineering System Using Neural Network EnsembleLixia Pan, Y.R. Zhang, Maosen Cao — 2015
• Prediction of Field Permeability Using by Artificial Neural NetworkYoung‐Su Kim, Sung-Gwan Jung, Dae-Man Kim — 2009
• Towards a generic neural network model for the prediction of daily streamflow in ungauged boreal plain watershedsMohamed H. Nour, Daniel W. Smith, Mohamed Gamal El‐Din — 2008
• Prediction of unconfined compressive strength of geopolymer stabilized clayey soil using Artificial Neural NetworkRuhul Amin Mozumder, Aminul Islam Laskar — 2015
• A New Prediction Model for Slope Stability AnalysisAzadeh Rashed — 2014

Related papers

• Learning internal representations by error propagationDavid E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams — 1986
• An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated dataJulian D. Olden, Michael Joy, Russell G. Death — 2004
• Training feedforward networks with the Marquardt algorithmMartin Hagan, Mohammad Bagher Menhaj — 1994
• Multilayer feedforward networks are universal approximatorsKurt Hornik, Maxwell B. Stinchcombe, Halbert White — 1989
• Neural Networks: A Comprehensive FoundationSimon Haykin — 1998
• Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networksJulian D. Olden, Donald A. Jackson — 2002
• Review and comparison of methods to study the contribution of variables in artificial neural network modelsMuriel Gevrey, Ioannis Dimopoulos, Sovan Lek — 2003
• Neural network models to study relationships between lead concentration in grasses and permanent urban descriptors in Athens city (Greece)Ioannis Dimopoulos, J. Chronopoulos, A. Chronopoulou‐Sereli — 1999
• Seismic liquefaction potential assessed by neural networksAnthony T.C. Goh — 1994
• Application of neural networks to modelling nonlinear relationships in ecologySovan Lek, M. DELACOSTE, Philippe Baran — 1996