Illuminating the "black box": A randomization approach for understanding variable contributions in artificial neural networks

Ecological Modelling

Volumn 154, Issue 1-2, 2002, Pages 135-150

  Olden, Julian D ^a,b   Jackson, Donald A ^a  

^a UNIVERSITY OF TORONTO   (Canada)

^b Department of Environmental and Radiological Health Sciences   (United States)

Author keywords

Connection weights; Garson's algorithm; Neural Interpretation Diagram; Sensitivity analysis; Statistical models

Indexed keywords

ARTIFICIAL NEURAL NETWORK; ECOLOGICAL MODELING; SENSITIVITY ANALYSIS;

EID: 0037102687     PISSN: 03043800     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0304-3800(02)00064-9     Document Type: Article

References (49)

1. Analysis and prediction of the fluctuation of sardine abundance using a neural network
2. Microsatellites and artificial neural networks: Tools for the discrimination between natural and hatchery brown trout (Salmo trutta, L.) in Atlantic populations
3. Predicting conductivity and acidity for small streams using neural networks
4. The use of neural networks to assess fish abundance and spatial occupancy in the littoral zone of a mesotrophic lake
5. Abundance, diversity, and structure of freshwater invertebrates and fish communities: An artificial neural network approach
6. A neural network model for forecasting fish stock recruitment
7. Neural networks: A review from a statistical perspective
8. Discussions of the possible use of neural network algorithms in ecological modeling
9. Use of some sensitivity criteria for choosing networks with good generalization
10. Neural network models to study relationships between lead concentration in grasses and permanent urban descriptors in Athens city (Greece)
11. The potential for computer-aided identification in biodiversity research
12. Interpreting neural-network connection weights
13. Recursive stochastic algorithms for global optimization in Rd.
14. Back-propagation neural networks for modeling complex systems
15. Predicting the structure and diversity of young-of-the-year fish assemblages in large rivers
16. Energy availability and habitat heterogeneity predict global riverine fish diversity
17. Multilayer feedforward networks are universal approximators
18. Predicting fish yield of African lakes using neural networks
19. Improved estimation, using neural networks, of the food consumption of fish populations
20. Role of some environmental variables in trout abundance models using neural networks
21. Application of neural networks to modeling nonlinear relationships in ecology
22. Artificial neural networks as a tool in ecological modeling, an introduction
23. Predictive models of collembolan diversity and abundance in a riparian habitat
24. Comparing discriminant analysis, neural networks and logistic regression for predicting species distributions: A case study with a Himalayan river bird
25. Predicting the abundance of minnow Phoxinus phoxinus (Cyprinidae) in the River Ariege (France) using artificial neural networks
26. The use of artificial neural networks to predict the presence of small-bodied fish in a river
27. Predicting local fish species richness in the Garonne River basin
28. Factors affecting fish species richness in Ontario lakes
29. An artificial neural network approach for studying phytoplankton succession
30. Torturing data for the sake of generality: How valid are our regression models?
31. Fish-habitat relationships in lakes: Gaining predictive and explanatory insight by using artificial neural networks
32. An artificial neural network approach to spatial habitat modeling with interspecific interaction
33. Prediction of functional characteristics of ecosystems: A comparison of artificial neural networks and regression models
34. When networks disagree: Ensemble methods for hybrid neural networks
35. Neural networks and related methods for classification
36. Statistical ideas for selecting network architectures
37. Learning representations by back-propagation errors
38. Advances in neural network modeling of phytoplankton primary production
39. Developing an empirical model of phytoplankton primary production: A neural network case study
40. Modeling water quality, bioindication and population dynamics in lotic ecosystems using neural networks
41. Environmental impact prediction using neural network modeling. An example in wildlife damage
42. Learning in artificial neural networks: A statistical perspective
43. Stacked generalization