English

Efficient Learning of Sparse Invariant Representations

Computer Vision and Pattern Recognition 2011-05-27 v1 Neural and Evolutionary Computing

Abstract

We propose a simple and efficient algorithm for learning sparse invariant representations from unlabeled data with fast inference. When trained on short movies sequences, the learned features are selective to a range of orientations and spatial frequencies, but robust to a wide range of positions, similar to complex cells in the primary visual cortex. We give a hierarchical version of the algorithm, and give guarantees of fast convergence under certain conditions.

Keywords

Cite

@article{arxiv.1105.5307,
  title  = {Efficient Learning of Sparse Invariant Representations},
  author = {Karol Gregor and Yann LeCun},
  journal= {arXiv preprint arXiv:1105.5307},
  year   = {2011}
}

Comments

9 pages + 6 supplement pages

R2 v1 2026-06-21T18:13:06.606Z