Perceiving Without Learning: From Spirals to Inside/Outside Relations

Abstract

As a benchmark task, the spiral problem is well known in neural net(cid:173) works. Unlike previous work that emphasizes learning, we approach the problem from a generic perspective that does not involve learning. We point out that the spiral problem is intrinsically connected to the in(cid:173) side/outside problem. A generic solution to both problems is proposed based on oscillatory correlation using a time delay network. Our simu(cid:173) lation results are qualitatively consistent with human performance, and we interpret human limitations in terms of synchrony and time delays, both biologically plausible. As a special case, our network without time delays can always distinguish these figures regardless of shape, position, size, and orientation.

Cite

Text

Chen and Wang. "Perceiving Without Learning: From Spirals to Inside/Outside Relations." Neural Information Processing Systems, 1998.

Markdown

[Chen and Wang. "Perceiving Without Learning: From Spirals to Inside/Outside Relations." Neural Information Processing Systems, 1998.](https://mlanthology.org/neurips/1998/chen1998neurips-perceiving/)

BibTeX

@inproceedings{chen1998neurips-perceiving,
  title     = {{Perceiving Without Learning: From Spirals to Inside/Outside Relations}},
  author    = {Chen, Ke and Wang, DeLiang L.},
  booktitle = {Neural Information Processing Systems},
  year      = {1998},
  pages     = {10-16},
  url       = {https://mlanthology.org/neurips/1998/chen1998neurips-perceiving/}
}