Evaluating the Contribution of Top-Down Feedback and Post-Learning Reconstruction

@inproceedings{Achler2011EvaluatingTC,
  title={Evaluating the Contribution of Top-Down Feedback and Post-Learning Reconstruction},
  author={Tsvi Achler and L. Bettencourt},
  booktitle={BICA},
  year={2011}
}
Deep generative models and their associated top-down architecture are gaining popularity in neuroscience and computer vision. In this paper we link our previous work with regulatory feedback networks to generative models. We show that generative model’s and regulatory feedback model’s equations can share the same fixed points. Thus, phenomena observed using regulatory feedback can also apply to generative models. This suggests that generative models can also be developed to identify mixtures of… Expand
10 Citations
Supervised Generative Reconstruction: An Efficient Way To Flexibly Store and Recognize Patterns
  • PDF
Image Segmentation Using a Sparse Coding Model of Cortical Area V1
  • 46
  • PDF
Towards Bridging the Gap Between Pattern Recognition and Symbolic Representation Within Neural Networks
  • 3
  • PDF
Symbolic neural networks for cognitive capacities
  • 16
  • PDF
Artificial General Intelligence Begins With Recognition: Evaluating the Flexibility of Recognition
  • 1
  • PDF
Classifiers for Regulatory Feedback Networks Using AB-Divergences

References

SHOWING 1-10 OF 30 REFERENCES
Forming sparse representations by local anti-Hebbian learning
  • P. Földiák
  • Computer Science, Medicine
  • Biological Cybernetics
  • 2004
  • 422
  • PDF
Input Feedback Networks: Classification and Inference Based on Network Structure
  • 21
  • PDF
Development of low entropy coding in a recurrent network.
  • 116
Reducing the Dimensionality of Data with Neural Networks
  • 12,239
  • PDF
Independent Component Analysis
  • 1,291
  • PDF
Shedding weights: More with less
  • Tsvi Achler, C. Omar, E. Amir
  • Computer Science
  • 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)
  • 2008
  • 11
  • PDF
Counting objects with biologically inspired regulatory-feedback networks
  • 14
  • PDF
Object classifiction with recurrent feedback neural networks
  • Tsvi Achler
  • Computer Science, Engineering
  • SPIE Defense + Commercial Sensing
  • 2007
  • 11
Computational modelling of visual attention
  • 3,915
  • PDF
...
1
2
3
...