dorsal/arxiv
View SchemaCan Neural Networks Recognize Parts?
| Authors | Koji Matsumura, Y-h. Taguchi |
|---|---|
| Categories | |
| ArXiv ID | q-bio/0410004 |
| URL | https://arxiv.org/abs/q-bio/0410004 |
Abstract
We have demonstrated neural networks can recognize parts by visual images. Input signals are gray scale photographs of objects consisting of some parts and output signals are their shapes. By training neural networks by a few set of images, without any supervision they become to be able to recognize the boundary between parts.
{
"annotation_id": "3e15ddd2-a64d-403b-ae8c-d140fe52cca7",
"date_created": "2026-03-02T18:01:31.877000Z",
"date_modified": "2026-03-02T18:01:31.877000Z",
"file_hash": "72b86aa480dd2b8ace5eda94cb861bea898ad3dbddcda44896d1d981b0238425",
"private": false,
"record": {
"abstract": "We have demonstrated neural networks can recognize parts by visual images.\nInput signals are gray scale photographs of objects consisting of some parts\nand output signals are their shapes. By training neural networks by a few set\nof images, without any supervision they become to be able to recognize the\nboundary between parts.",
"arxiv_id": "q-bio/0410004",
"authors": [
"Koji Matsumura",
"Y-h. Taguchi"
],
"categories": [
"q-bio.NC"
],
"title": "Can Neural Networks Recognize Parts?",
"url": "https://arxiv.org/abs/q-bio/0410004"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "a6b8f1bf-d9e2-4bc9-8700-75c725da9a85",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}