Selective Attention for Handwritten Digit Recognition

NeurIPS 1995 pp. 771-777

/neurips/1995/alpaydin1995neurips-selective/

Abstract

Completely parallel object recognition is NP-complete. Achieving a recognizer with feasible complexity requires a compromise be(cid:173) tween parallel and sequential processing where a system selectively focuses on parts of a given image, one after another. Successive fixations are generated to sample the image and these samples are processed and abstracted to generate a temporal context in which results are integrated over time. A computational model based on a partially recurrent feedforward network is proposed and made cred(cid:173) ible by testing on the real-world problem of recognition of hand(cid:173) written digits with encouraging results.

PDF NeurIPS Semantic Scholar

Cite

Text

Alpaydin. "Selective Attention for Handwritten Digit Recognition." Neural Information Processing Systems, 1995.

Markdown

[Alpaydin. "Selective Attention for Handwritten Digit Recognition." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/alpaydin1995neurips-selective/)

BibTeX

@inproceedings{alpaydin1995neurips-selective,
  title     = {{Selective Attention for Handwritten Digit Recognition}},
  author    = {Alpaydin, Ethem},
  booktitle = {Neural Information Processing Systems},
  year      = {1995},
  pages     = {771-777},
  url       = {https://mlanthology.org/neurips/1995/alpaydin1995neurips-selective/}
}