Abstract | ||
---|---|---|
A key goal in the study of visual processing is to obtain a comprehensive description of the relationship between visual stimuli and neuronal responses. One way to guide the search for models is to use a general nonparametric regression algorithm, such as a neural network. We have developed a multilayer feed-forward network algorithm that can be used to characterize nonlinear stimulus-response mapping functions of neurons in primary visual cortex (area V1) using natural image stimuli. The network is capable of extracting several known V1 response properties such as: orientation and spatial frequency tuning, the spatial phase invariance of complex cells, and direction selectivity. We present details of a method for training networks and visualizing their properties. We also compare how well conventional explicit models and those developed using neural networks can predict novel responses to natural scenes. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1016/j.neunet.2004.03.008 | Neural Networks |
Keywords | Field | DocType |
prediction,multi layer perceptron,neural network,feed forward,receptive field,spatial frequency,nonparametric regression | Receptive field,Computer vision,Visual processing,Visual cortex,Nonparametric regression,Multilayer perceptron,Artificial intelligence,Artificial neural network,Machine learning,Visual perception,Mathematics,Spatial frequency | Journal |
Volume | Issue | ISSN |
17 | 5-6 | 0893-6080 |
Citations | PageRank | References |
16 | 1.01 | 3 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ryan J. Prenger | 1 | 24 | 1.89 |
Michael C.-K. Wu | 2 | 16 | 1.01 |
Stephen V. David | 3 | 48 | 6.31 |
Jack L. Gallant | 4 | 183 | 11.08 |