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 Lu{\'i}s M. A. 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… CONTINUE READING

From This Paper

Topics from this paper.

References

Publications referenced by this paper.
Showing 1-10 of 28 references

Counting objects with biologically inspired regulatory-feedback networks

2009 International Joint Conference on Neural Networks • 2009
View 3 Excerpts

Using non-oscillatory dynamics to disambiguate simultaneous patterns

2009 International Joint Conference on Neural Networks • 2009
View 4 Excerpts

Shedding weights: More with less

2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence) • 2008
View 4 Excerpts

and R . R . Salakhutdinov . " Reducing the dimensionality of data with neural networks

T. Achler, E. Amir
Input Feedback Networks : Classification and Inference Based on Network Structure , Artificial General Intelligence Proceedings V • 2008

Object classification with recurrent feedback neural networks.

T. Achler
Proc. SPIE Evolutionary and Bio-inspired Computation: Theory and Applications • 2007
View 1 Excerpt

A theory of cortical responses.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences • 2005

Neuronal circuits of the neocortex.

Annual review of neuroscience • 2004
View 1 Excerpt

Similar Papers

Loading similar papers…