Name
Abstract | ||
|---|---|---|
Biological organisms need to accurately infer which features of their environment predict future rewards and punishments for survival sake. This problem resembles linear regression, which finds parameter values expressing the linear relationship between features and an outcome. The least mean squares regression method generalizes well when there is little system noise and at least as many training data points (experiences) as input features. When this is not the case, feature selection may be applied to eliminate irrelevant features and improve generalization. Here, we show a biologically plausible approach to feature selection that computes the maximum likelihood estimate of Pearl's “Noisy OR” model. We show that this results in highlighting the features that are most correlated with the outcome at the expense of the least correlated. We extend this “relative correlation” approach to represent global inhibitory features and show that as additive noise and the number of irrelevant features are increased, relative correlation leads to substantially less prediction error on test data than does least means squares in a simple linear regression task. We demonstrate how relative correlation can be implemented in a dual pathway neural network and discuss some similarities between it and the basal ganglia. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/IJCNN.2013.6706813 | Neural Networks |
Keywords | Field | DocType |
biology computing,least mean squares methods,maximum likelihood estimation,neural nets,regression analysis,additive noise,basal ganglia,biological organisms,biologically plausible approach,biologically plausible feature selection,dual pathway neural network,global inhibitory features,irrelevant features,least mean squares regression method,least means squares,less prediction error,linear regression task,linear relationship,maximum likelihood estimate,relative correlation approach,system noise,training data points | Feature selection,Pattern recognition,Generalized least squares,Iteratively reweighted least squares,Robust regression,Artificial intelligence,Simple linear regression,Variance function,Non-linear least squares,Total least squares,Machine learning,Mathematics | Conference |
ISSN | ISBN | Citations |
2161-4393 | 978-1-4673-6128-6 | 1 |
PageRank | References | Authors |
0.38 | 4 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Patrick C. Connor | 1 | 11 | 1.95 |
| Thomas P. Trappenberg | 2 | 82 | 18.17 |