Acquisition of nonlinear forward optics in generative models: Two-stage "downside-up" learning for occluded vision

@article{Tajima2011AcquisitionON,
  title={Acquisition of nonlinear forward optics in generative models: Two-stage "downside-up" learning for occluded vision},
  author={Satohiro Tajima and Masataka Watanabe},
  journal={Neural networks : the official journal of the International Neural Network Society},
  year={2011},
  volume={24 2},
  pages={148-58}
}
We propose a two-stage learning method which implements occluded visual scene analysis into a generative model, a type of hierarchical neural network with bi-directional synaptic connections. Here, top-down connections simulate forward optics to generate predictions for sensory driven low-level representation, whereas bottom-up connections function to send the prediction error, the difference between the sensory based and the predicted low-level representation, to higher areas. The prediction… CONTINUE READING