554:
77:
The local features are extracted by S-cells, and these features' deformation, such as local shifts, are tolerated by C-cells. Local features in the input are integrated gradually and classified in the higher layers. The idea of local feature integration is found in several other models, such as the
99:
There are various kinds of neocognitron. For example, some types of neocognitron can detect multiple patterns in the same input by using backward signals to achieve
362:
Fukushima, Kunihiko (April 1980). "Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position".
69:
The neocognitron is a natural extension of these cascading models. The neocognitron consists of multiple types of cells, the most important of which are called
532:
595:
619:
245:
424:
Fukushima, Kunihiko (1987). "A hierarchical neural network model for selective attention". In
Eckmiller, R.; Von der Malsburg, C. (eds.).
614:
399:
Fukushima, Kunihiko; Miyake, S.; Ito, T. (1983). "Neocognitron: a neural network model for a mechanism of visual pattern recognition".
86:
92:
161:[Neural network model for a mechanism of pattern recognition unaffected by shift in position — Neocognitron —].
80:
40:
588:
112:
24:
561:
32:
581:
137:
66:, and also proposed a cascading model of these two types of cells for use in pattern recognition tasks.
446:
192:
132:
122:
100:
36:
412:
387:
216:
28:
499:
379:
292:
241:
235:
208:
565:
489:
481:
454:
404:
371:
282:
274:
200:
158:
127:
450:
196:
494:
469:
287:
262:
51:
47:
177:
608:
391:
117:
521:
517:
485:
416:
278:
220:
62:
553:
56:
459:
434:
408:
503:
296:
212:
54:
in 1959. They found two types of cells in the visual primary cortex called
538:
526:
383:
204:
375:
470:"Receptive fields of single noreones in the cat's striate cortex"
263:"Receptive fields of single neurones in the cat's striate cortex"
237:
Brain and visual perception: the story of a 25-year collaboration
569:
46:
The neocognitron was inspired by the model proposed by
176:
LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey (2015).
401:IEEE Transactions on Systems, Man, and Cybernetics
159:"位置ずれに影響されないパターン認識機構の神経回路のモデル --- ネオコグニトロン ---"
589:
234:David H. Hubel and Torsten N. Wiesel (2005).
8:
240:. Oxford University Press US. p. 106.
596:
582:
533:Neocognitron resources at Visiome Platform
493:
458:
345:
333:
321:
309:
286:
39:tasks, and served as the inspiration for
149:
31:in 1979. It has been used for Japanese
261:Hubel, DH; Wiesel, TN (October 1959).
7:
550:
548:
527:NeoCognitron by Ing. Gabriel Minarik
157:Fukushima, Kunihiko (October 1979).
165:(in Japanese). J62-A (10): 658–665.
568:. You can help Knowledge (XXG) by
468:Hubel, D.H.; Wiesel, T.N. (1959).
428:. Springer-Verlag. pp. 81–90.
14:
33:handwritten character recognition
16:Type of artificial neural network
552:
23:is a hierarchical, multilayered
486:10.1113/jphysiol.1959.sp006308
279:10.1113/jphysiol.1959.sp006308
1:
620:Artificial intelligence stubs
535:- includes MATLAB environment
41:convolutional neural networks
529:- application (C#) and video
433:Fukushima, Kunihiko (2007).
81:Convolutional Neural Network
636:
615:Artificial neural networks
547:
541:- a Neocognitron simulator
460:10.4249/scholarpedia.1717
409:10.1109/TSMC.1983.6313076
113:Artificial neural network
25:artificial neural network
562:artificial intelligence
403:. SMC-13 (3): 826–834.
564:-related article is a
364:Biological Cybernetics
138:Unsupervised learning
451:2007SchpJ...2.1717F
205:10.1038/nature14539
197:2015Natur.521..436L
133:Self-organizing map
123:Pattern recognition
101:selective attention
37:pattern recognition
376:10.1007/bf00344251
348:, pp. 81, 85.
29:Kunihiko Fukushima
577:
576:
247:978-0-19-517618-6
191:(7553): 436–444.
627:
598:
591:
584:
556:
549:
507:
497:
464:
462:
429:
426:Neural computers
420:
395:
349:
343:
337:
331:
325:
319:
313:
307:
301:
300:
290:
258:
252:
251:
231:
225:
224:
182:
173:
167:
166:
154:
90:method, and the
635:
634:
630:
629:
628:
626:
625:
624:
605:
604:
603:
602:
545:
514:
467:
432:
423:
398:
361:
358:
353:
352:
344:
340:
332:
328:
320:
316:
308:
304:
260:
259:
255:
248:
233:
232:
228:
180:
178:"Deep learning"
175:
174:
170:
156:
155:
151:
146:
128:Receptive field
109:
17:
12:
11:
5:
633:
631:
623:
622:
617:
607:
606:
601:
600:
593:
586:
578:
575:
574:
557:
543:
542:
536:
530:
524:
513:
512:External links
510:
509:
508:
480:(3): 574–591.
465:
435:"Neocognitron"
430:
421:
396:
370:(4): 193–202.
357:
354:
351:
350:
346:Fukushima 1987
338:
334:Fukushima 2007
326:
322:Fukushima 1987
314:
310:Fukushima 1987
302:
253:
246:
226:
168:
148:
147:
145:
142:
141:
140:
135:
130:
125:
120:
115:
108:
105:
15:
13:
10:
9:
6:
4:
3:
2:
632:
621:
618:
616:
613:
612:
610:
599:
594:
592:
587:
585:
580:
579:
573:
571:
567:
563:
558:
555:
551:
546:
540:
537:
534:
531:
528:
525:
523:
519:
516:
515:
511:
505:
501:
496:
491:
487:
483:
479:
475:
471:
466:
461:
456:
452:
448:
444:
440:
436:
431:
427:
422:
418:
414:
410:
406:
402:
397:
393:
389:
385:
381:
377:
373:
369:
365:
360:
359:
355:
347:
342:
339:
335:
330:
327:
324:, p. 84.
323:
318:
315:
312:, p. 83.
311:
306:
303:
298:
294:
289:
284:
280:
276:
273:(3): 574–91.
272:
268:
264:
257:
254:
249:
243:
239:
238:
230:
227:
222:
218:
214:
210:
206:
202:
198:
194:
190:
186:
179:
172:
169:
164:
160:
153:
150:
143:
139:
136:
134:
131:
129:
126:
124:
121:
119:
118:Deep learning
116:
114:
111:
110:
106:
104:
102:
97:
95:
94:
89:
88:
83:
82:
76:
72:
67:
65:
64:
59:
58:
53:
49:
44:
42:
38:
34:
30:
26:
22:
570:expanding it
559:
544:
522:Scholarpedia
518:Neocognitron
477:
473:
442:
439:Scholarpedia
438:
425:
400:
367:
363:
341:
329:
317:
305:
270:
266:
256:
236:
229:
188:
184:
171:
162:
152:
98:
91:
85:
79:
74:
70:
68:
63:complex cell
61:
55:
45:
27:proposed by
21:neocognitron
20:
18:
445:(1): 1717.
163:Trans. IECE
84:model, the
57:simple cell
609:Categories
356:References
267:J. Physiol
35:and other
474:J Physiol
392:206775608
539:Beholder
504:14403679
297:14403679
213:26017442
107:See also
96:method.
75:C-cells.
495:1363130
447:Bibcode
417:8235461
384:7370364
288:1363130
221:3074096
193:Bibcode
71:S-cells
502:
492:
415:
390:
382:
295:
285:
244:
219:
211:
185:Nature
52:Wiesel
50:&
560:This
413:S2CID
388:S2CID
217:S2CID
181:(PDF)
144:Notes
48:Hubel
566:stub
500:PMID
380:PMID
293:PMID
242:ISBN
209:PMID
87:SIFT
73:and
60:and
19:The
520:on
490:PMC
482:doi
478:148
455:doi
405:doi
372:doi
283:PMC
275:doi
271:148
201:doi
189:521
93:HoG
611::
498:.
488:.
476:.
472:.
453:.
441:.
437:.
411:.
386:.
378:.
368:36
366:.
291:.
281:.
269:.
265:.
215:.
207:.
199:.
187:.
183:.
103:.
43:.
597:e
590:t
583:v
572:.
506:.
484::
463:.
457::
449::
443:2
419:.
407::
394:.
374::
336:.
299:.
277::
250:.
223:.
203::
195::
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.