A Hebbian/Anti-Hebbian Neural Network for Linear Subspace Learning: A Derivation from Multidimensional Scaling of Streaming Data

@article{Pehlevan2015AHN,
  title={A Hebbian/Anti-Hebbian Neural Network for Linear Subspace Learning: A Derivation from Multidimensional Scaling of Streaming Data},
  author={Cengiz Pehlevan and Tao Hu and Dmitri B. Chklovskii},
  journal={Neural Computation},
  year={2015},
  volume={27},
  pages={1461-1495}
}
Neural network models of early sensory processing typically reduce the dimensionality of streaming input data. Such networks learn the principal subspace, in the sense of principal component analysis, by adjusting synaptic weights according to activity-dependent learning rules. When derived from a principled cost function, these rules are nonlocal and hence biologically implausible. At the same time, biologically plausible local rules have been postulated rather than derived from a principled… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 32 CITATIONS

A mixed-mode array computing architecture for online dictionary learning

  • 2017 IEEE International Symposium on Circuits and Systems (ISCAS)
  • 2017
VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Normative Theory of Adaptive Dimensionality Reduction in Neural Networks

VIEW 9 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

Optimization theory of Hebbian/anti-Hebbian networks for PCA and whitening

  • 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton)
  • 2015
VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Efficient Principal Subspace Projection of Streaming Data Through Fast Similarity Matching

  • 2018 IEEE International Conference on Big Data (Big Data)
  • 2018
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 42 REFERENCES

On a connection between kernel PCA and metric multidimensional scaling

C. Williams
  • Advances in neural information processing systems,
  • 2001
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Projection approximation subspace tracking

  • IEEE Trans. Signal Processing
  • 1995
VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

Introduction to Linear Algebra

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Principal component neural networks — Theory and applications

  • Pattern Analysis and Applications
  • 1998
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

On lines and planes of closest fit to systems of points in space

K. Pearson
  • Philos Mag.,
  • 1901
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

A neuron as a signal processing device

  • 2013 Asilomar Conference on Signals, Systems and Computers
  • 2013
VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL

Eye, brain, and vision. New York: Scientific American Library/ Scientific American Books

D. H. Hubel
  • 1995
VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…