Neocognitron capable of incremental learning
Neural Networks
Journal of Cognitive Neuroscience
A model of angle selectivity development in visual area V2
Neurocomputing
Selective motion analysis based on dynamic visual saliency map model
ICAISC'06 Proceedings of the 8th international conference on Artificial Intelligence and Soft Computing
Hi-index | 0.00 |
We develop a neural network architecture to help model the creation of visual temporal object representations. We take visual input to be hard-wired up to and including V1 (as an orientation-filtering system). We then develop architectures for afferents to V2 and thence to V4, both of which are trained by a causal Hebbian law. We use an incremental approach, using sequences of increasingly complex stimuli at an increasing level of the hierarchy. The V2 representations are shown to encode angles, and V4 is found sensitive to shapes embedded in figures. These results are compared to recent experimental data, supporting the incremental training scheme and associated architecture.