186:
66:
25:
581:(more precisely, the log-EM algorithm). The merit of the speedup by the alpha-EM over the log-EM is due to the ability to utilize the past information. Such a usage of the messages from the past brought about the alpha-HMM estimation algorithm (alpha-hidden Markov model estimation algorithm) that is a generalized and faster version of the
312:
599:
algorithms; the harmonic competition and the multiple descent cost competition. The former realizes the multiple-object optimization. The latter admits deformable centroids. Both algorithms generalize the batch-mode vector quantization (simply called,
577:: The use of the alpha-logarithmic likelihood ratio in learning cycles generated the alpha-EM algorithm (alpha-Expectation maximization algorithm). Because the alpha-logarithm includes the usual logarithm, the alpha-EM algorithm contains the
532:
Since 1996, he was a
Professor of Waseda University, Department of Computer Science and Engineering. From 2011 to 2013, he was the director of the Media Network Center of Waseda University. At the
563:. Studies on the competitive learning (vector quantization) for his Ph.D. at Stanford University brought about his succeeding works on machine learning contributions. Studies on stochastic
1177:
Matsuyama, Yasuo; Noguchi, Keita; Hatakeyama, Takashi; Ochiai, Nimiko; Hori, Tatsuro (2010-08-28). "Brain Signal
Recognition and Conversion towards Symbiosis with Ambulatory Humanoids".
1364:
482:
Upon the completion of the doctoral work at Waseda
University, he was dispatched to the United States as a Japan-U.S. exchange fellow by the joint program of the
567:
for his Dr. Engineering at Waseda
University set off applications of biological signals to the machine learning. Thus, his works can be grouped reflecting these
479:. There, he contributed to the spiking neurons with stochastic pulse-frequency modulation. Advisors were Jun’ichi Takagi, Kageo, Akizuki, and Katsuhiko Shirai.
828:
Matsuyama, Yasuo; Shirai, Katsuhiko; Akizuki, Kageo (1974-09-01). "On some properties of stochastic information processes in neurons and neuron populations".
1398:
1144:
Horie, Teruki; Shikano, Akihiro; Iwase, Hiromichi; Matsuyama, Yasuo (2015-11-09). "Learning
Algorithms and Frame Signatures for Video Similarity Ranking".
483:
94:
74:
619:
578:
761:
1393:
533:
491:
933:
Matsuyama, Y. (March 2003). "The alpha;-EM algorithm: surrogate likelihood maximization using alpha;-logarithmic information measures".
729:
1074:
Matsuyama, Y. (January 1998). "Multiple descent cost competition: restorable self-organization and multimedia information processing".
425:
Waseda
University: Jun'ichi Takagi, Kageo Akizuki, and Kastuhiko Shirai for Dr. Engineering Stanford University: Robert M. Gray for PhD
1307:
Matsuyama, Y.; Gray, R. (April 1982). "Voice Coding and Tree
Encoding Speech Compression Systems Based Upon Inverse Filter Matching".
1194:
1161:
287:
269:
167:
52:
207:
200:
642:
On the class of the vector quantization and competitive learning, he contributed to generate and identify the hierarchy of VQs.
635:
38:
1210:
Matsuyama, Yasuo; Shozawa, Michitaro; Yokote, Ryota (2015). "Brain signal׳s low-frequency fits the continuous authentication".
250:
148:
222:
120:
494:. Through this exchange program, he completed his Ph.D. program at Stanford University in 1978. The dissertation title is
98:
90:
605:
229:
127:
459:
Matsuyama is a
Professor Emeritus and an Honorary Researcher of the Research Institute of Science and Engineering of
79:
196:
83:
236:
134:
687:
The above theories and applications work as contributions to IoCT (Internet of
Collaborative Things) and IoXT (
1117:
Katsumata, Naoto; Matsuyama, Yasuo (2005). "Database retrieval for similar images using ICA and PCA bases".
218:
116:
529:, Japan (the final position was a professor and chairperson of the Information and System Sciences Major).
1388:
1237:
Gray, R.; Buzo, A.; Gray, A.; Matsuyama, Y. (August 1980). "Distortion measures for speech processing".
1383:
1181:. Lecture Notes in Computer Science. Vol. 6334. Springer, Berlin, Heidelberg. pp. 101–111.
977:
758:
680:
646:
VQ ⇔ {batch mode VQ, and learning VQ} ⊂ {harmonic competition} ⊂ {multiple descent cost competition}.
623:
596:
44:
1024:
Matsuyama, Y. (May 1996). "Harmonic competition: a self-organizing multiple criteria optimization".
536:
of March 11, 2011, he was in charge of the safety inquiry of 65,000 students, staffs and faculties.
631:
627:
601:
582:
503:
498:. There, he contributed to the theory of probabilistic distortion measures and its applications to
816:
741:
2004: Best Paper Award for
Application Oriented Research from Asia Pacific Neural Network Assembly
673:
Decomposition of DNA sequences by the independent component analysis (US Patent: US 8,244,474 B2).
1001:
912:
861:
771:
719:
713:
526:
968:
Matsuyama, Y. (July 2017). "The Alpha-HMM Estimation Algorithm: Prior Cycle Guides Fast Paths".
804:
471:
Matsuyama received his bachelor’s, master’s and doctoral degrees in electrical engineering from
105:
1324:
1289:
1254:
1190:
1157:
1099:
1091:
1049:
1041:
993:
950:
904:
896:
853:
845:
487:
475:
in 1969, 1971, and 1974 respectively. The dissertation title for the Doctor of Engineering is
472:
460:
311:
243:
141:
1316:
1281:
1246:
1219:
1182:
1149:
1126:
1083:
1033:
985:
942:
888:
837:
676:
556:
449:
420:
381:
779:
Best Paper Award from the Institute of Electronics, Information and Communication Engineers
664:
Bipedal humanoid operations via invasive and noninvasive brain signals as well as gestures.
778:
765:
614:: Matsuyama contributed to generate and identify the hierarchy of the above algorithms.
592:
499:
453:
385:
981:
701:
1148:. Lecture Notes in Computer Science. Vol. 9489. Springer, Cham. pp. 147–157.
746:
Fellow Award from the Institute of Electronics, Information and Communication Engineers
564:
507:
1342:
1377:
707:
1005:
879:
Matsuyama, Y. (1976-09-01). "A note on stochastic modeling of shunting inhibition".
865:
670:
Self-organization and emotional feature injection based on the competitive learning.
1130:
916:
1223:
1186:
1153:
815:
Matsuyama, Yasuo (1978-08). "Process Distortion Measures and Signal Processing",
745:
539:
Since 2017, Matsuyama is a Professor Emeritus and an Honorary Researcher of the
185:
1250:
688:
1359:
1320:
1272:
Matsuyama, Y.; Gray, R. (January 1981). "Universal tree encoding for speech".
437:
1328:
1293:
1285:
1258:
1095:
1045:
997:
989:
954:
900:
849:
946:
725:
1103:
1053:
857:
908:
803:
Matsuyama, Yasuo (1974-03). "Studies on Stochastic Modeling of neurons",
358:
Waseda University (Dr. Engineering, 1974) Stanford University (PhD, 1978)
338:
892:
841:
1087:
1037:
738:
2006: LSI Intellectual Property Design Award from the LSI IP Committee
708:
Best Textbook Award by the Japanese Society of Information Processing
657:
of his led to the applications to huma-aware information processing.
400:
540:
541:
Research Institute of Science and Engineering of Waseda University
1368:
733:
817:
http://www.f.waseda.jp/yasuo2/MatsuyamaStanfordDissertation.pdf
759:
Outstanding Paper Award of IEEE Transactions on Neural Networks
179:
104:
from the article and its talk page, especially if potentially
59:
18:
1239:
IEEE Transactions on Acoustics, Speech, and Signal Processing
805:
http://www.f.waseda.jp/yasuo2/MatsuyamaWasedaDissertation.pdf
518:
From 1977 to 1078, Matsuyama was a research assistant at the
519:
774:
for contributions to learning algorithms with competition.
604:) and the successive-mode vector quantization (or, called
784:
752:
1360:
Yasuo Matsuyama, Professor Emeritus of Waseda University
714:
Fellow of the Japanese Society of Information Processing
612:
A hierarchy from the alpha-EM to the vector quantization
544:
1343:"IEEE Fellows 1998 | IEEE Communications Society"
783:
1989: Telecommunication System Promotion Award of the
543:. Since 2018, he serves as an acting president of the
595:
studies at Stanford, Matsuyama developed generalized
520:
Information Systems Laboratory of Stanford University
1119:
Engineering Applications of Artificial Intelligence
667:
Continuous authentication of uses by brain signals.
433:
419:
399:
391:
377:
362:
354:
346:
321:
302:
751:2001: Telecommunication System Major Award of the
651:Applications to Human-aware information processing
448:(born March 23, 1947) is a Japanese researcher in
411:Process Distortion Measures and Signal Processing
585:estimation algorithm (HMM estimation algorithm).
496:Process Distortion Measures and Signal Processing
661:Retrieval systems for similar images and videos.
726:Y. Dote Memorial Best Paper Award of CSTST 2008
8:
689:http://www.asc-events.org/ASC17/Workshop.php
559:and human-aware information processing have
438:http://www.f.waseda.jp/yasuo2/en/index.html
53:Learn how and when to remove these messages
484:Japan Society for the Promotion of Science
406:Studies on Stochastic Modeling of Neurons
310:
299:
97:about living persons that is unsourced or
785:Telecommunications Advancement Foundation
753:Telecommunications Advancement Foundation
477:Studies on Stochastic Modeling of Neurons
288:Learn how and when to remove this message
270:Learn how and when to remove this message
168:Learn how and when to remove this message
408:(Dr. Engineering from Waseda University)
1274:IEEE Transactions on Information Theory
935:IEEE Transactions on Information Theory
796:
575:Statistical machine learning algorithms
525:From 1979 to 1996, he was a faculty of
970:IEEE Transactions on Signal Processing
589:Competitive learning on empirical data
395:Waseda University, Stanford University
206:Please improve this article by adding
702:e-Teaching Award of Waseda University
545:Waseda Electrical Engineering Society
7:
1076:IEEE Transactions on Neural Networks
1069:
1067:
1065:
1063:
1026:IEEE Transactions on Neural Networks
1019:
1017:
1015:
928:
926:
492:Institute of International Education
1399:Academic staff of Waseda University
1309:IEEE Transactions on Communications
316:At the 2017 HPC Connection Workshop
534:2011 Tōhoku earthquake and tsunami
14:
34:This article has multiple issues.
184:
64:
23:
42:or discuss these issues on the
1131:10.1016/j.engappai.2005.01.002
413:(PhD from Stanford University)
1:
1146:Neural Information Processing
208:secondary or tertiary sources
1394:Machine learning researchers
1224:10.1016/j.neucom.2014.08.084
1187:10.1007/978-3-642-15314-3_10
1154:10.1007/978-3-319-26532-2_17
606:learning vector quantization
502:with spectral clustering or
75:biography of a living person
102:must be removed immediately
1415:
1251:10.1109/tassp.1980.1163421
1321:10.1109/tcom.1982.1095512
679:of speech signals by the
429:
370:
309:
1286:10.1109/tit.1981.1056306
990:10.1109/tsp.2017.2692724
467:Early life and education
947:10.1109/tit.2002.808105
881:Biological Cybernetics
772:Fellow Award from IEEE
454:information processing
386:information processing
195:relies excessively on
89:Please help by adding
555:Matsuyama’s works on
681:competitive learning
624:competitive learning
597:competitive learning
591:: Starting from the
95:Contentious material
982:2017ITSP...65.3446M
628:vector quantization
602:vector quantization
583:hidden Markov model
504:vector quantization
893:10.1007/BF00364116
842:10.1007/BF00274585
764:2013-01-17 at the
593:speech compression
527:Ibaraki University
506:. His advisor was
366:Alpha-EM algorithm
16:Computer scientist
1179:Brain Informatics
1088:10.1109/72.655033
1038:10.1109/72.501723
976:(13): 3446–3461.
695:Awards and honors
488:Fulbright Program
473:Waseda University
461:Waseda University
443:
442:
372:Scientific career
298:
297:
290:
280:
279:
272:
254:
219:"Yasuo Matsuyama"
178:
177:
170:
152:
117:"Yasuo Matsuyama"
78:needs additional
57:
1406:
1347:
1346:
1339:
1333:
1332:
1304:
1298:
1297:
1269:
1263:
1262:
1234:
1228:
1227:
1207:
1201:
1200:
1174:
1168:
1167:
1141:
1135:
1134:
1114:
1108:
1107:
1071:
1058:
1057:
1021:
1010:
1009:
965:
959:
958:
930:
921:
920:
876:
870:
869:
825:
819:
813:
807:
801:
720:IEEE Life Fellow
677:Data compression
655:dual foundations
569:dual foundations
561:dual foundations
557:machine learning
452:and human-aware
450:machine learning
421:Doctoral advisor
384:and human-aware
382:Machine learning
335:
331:
329:
314:
300:
293:
286:
275:
268:
264:
261:
255:
253:
212:
188:
180:
173:
166:
162:
159:
153:
151:
110:
91:reliable sources
68:
67:
60:
49:
27:
26:
19:
1414:
1413:
1409:
1408:
1407:
1405:
1404:
1403:
1374:
1373:
1365:Yasuo Matsuyama
1356:
1351:
1350:
1341:
1340:
1336:
1306:
1305:
1301:
1271:
1270:
1266:
1236:
1235:
1231:
1209:
1208:
1204:
1197:
1176:
1175:
1171:
1164:
1143:
1142:
1138:
1116:
1115:
1111:
1073:
1072:
1061:
1023:
1022:
1013:
967:
966:
962:
932:
931:
924:
878:
877:
873:
827:
826:
822:
814:
810:
802:
798:
793:
766:Wayback Machine
697:
565:spiking neurons
553:
516:
508:Robert. M. Gray
500:speech encoding
469:
446:Yasuo Matsuyama
410:
355:Alma mater
342:
336:
333:
327:
325:
317:
305:
304:Yasuo Matsuyama
294:
283:
282:
281:
276:
265:
259:
256:
213:
211:
205:
201:primary sources
189:
174:
163:
157:
154:
111:
109:
88:
69:
65:
28:
24:
17:
12:
11:
5:
1412:
1410:
1402:
1401:
1396:
1391:
1386:
1376:
1375:
1372:
1371:
1362:
1355:
1354:External links
1352:
1349:
1348:
1334:
1315:(4): 711–720.
1299:
1264:
1245:(4): 367–376.
1229:
1212:Neurocomputing
1202:
1195:
1169:
1162:
1136:
1125:(6): 705–717.
1109:
1082:(1): 106–122.
1059:
1032:(3): 652–668.
1011:
960:
941:(3): 692–706.
922:
887:(3): 139–145.
871:
836:(3): 127–145.
820:
808:
795:
794:
792:
789:
788:
787:
781:
775:
768:
755:
749:
742:
739:
736:
722:
716:
710:
704:
696:
693:
685:
684:
674:
671:
668:
665:
662:
648:
647:
640:
639:
552:
549:
515:
512:
468:
465:
441:
440:
435:
431:
430:
427:
426:
423:
417:
416:
403:
397:
396:
393:
389:
388:
379:
375:
374:
368:
367:
364:
363:Known for
360:
359:
356:
352:
351:
348:
344:
343:
337:
332:March 23, 1947
323:
319:
318:
315:
307:
306:
303:
296:
295:
278:
277:
192:
190:
183:
176:
175:
99:poorly sourced
72:
70:
63:
58:
32:
31:
29:
22:
15:
13:
10:
9:
6:
4:
3:
2:
1411:
1400:
1397:
1395:
1392:
1390:
1389:Living people
1387:
1385:
1382:
1381:
1379:
1370:
1366:
1363:
1361:
1358:
1357:
1353:
1344:
1338:
1335:
1330:
1326:
1322:
1318:
1314:
1310:
1303:
1300:
1295:
1291:
1287:
1283:
1279:
1275:
1268:
1265:
1260:
1256:
1252:
1248:
1244:
1240:
1233:
1230:
1225:
1221:
1217:
1213:
1206:
1203:
1198:
1196:9783642153136
1192:
1188:
1184:
1180:
1173:
1170:
1165:
1163:9783319265315
1159:
1155:
1151:
1147:
1140:
1137:
1132:
1128:
1124:
1120:
1113:
1110:
1105:
1101:
1097:
1093:
1089:
1085:
1081:
1077:
1070:
1068:
1066:
1064:
1060:
1055:
1051:
1047:
1043:
1039:
1035:
1031:
1027:
1020:
1018:
1016:
1012:
1007:
1003:
999:
995:
991:
987:
983:
979:
975:
971:
964:
961:
956:
952:
948:
944:
940:
936:
929:
927:
923:
918:
914:
910:
906:
902:
898:
894:
890:
886:
882:
875:
872:
867:
863:
859:
855:
851:
847:
843:
839:
835:
831:
824:
821:
818:
812:
809:
806:
800:
797:
790:
786:
782:
780:
776:
773:
769:
767:
763:
760:
756:
754:
750:
747:
743:
740:
737:
735:
731:
727:
723:
721:
717:
715:
711:
709:
705:
703:
699:
698:
694:
692:
690:
682:
678:
675:
672:
669:
666:
663:
660:
659:
658:
656:
652:
645:
644:
643:
637:
633:
629:
625:
621:
617:
616:
615:
613:
609:
607:
603:
598:
594:
590:
586:
584:
580:
576:
572:
570:
566:
562:
558:
550:
548:
546:
542:
537:
535:
530:
528:
523:
521:
513:
511:
509:
505:
501:
497:
493:
489:
485:
480:
478:
474:
466:
464:
462:
457:
455:
451:
447:
439:
436:
432:
428:
424:
422:
418:
415:
412:
407:
404:
402:
398:
394:
390:
387:
383:
380:
376:
373:
369:
365:
361:
357:
353:
349:
345:
340:
334:(age 77)
324:
320:
313:
308:
301:
292:
289:
274:
271:
263:
252:
249:
245:
242:
238:
235:
231:
228:
224:
221: –
220:
216:
215:Find sources:
209:
203:
202:
198:
193:This article
191:
187:
182:
181:
172:
169:
161:
150:
147:
143:
140:
136:
133:
129:
126:
122:
119: –
118:
114:
113:Find sources:
107:
103:
100:
96:
92:
86:
85:
81:
76:
71:
62:
61:
56:
54:
47:
46:
41:
40:
35:
30:
21:
20:
1337:
1312:
1308:
1302:
1280:(1): 31–40.
1277:
1273:
1267:
1242:
1238:
1232:
1215:
1211:
1205:
1178:
1172:
1145:
1139:
1122:
1118:
1112:
1079:
1075:
1029:
1025:
973:
969:
963:
938:
934:
884:
880:
874:
833:
829:
823:
811:
799:
686:
654:
650:
649:
641:
611:
610:
588:
587:
579:EM-algorithm
574:
573:
568:
560:
554:
538:
531:
524:
517:
495:
481:
476:
470:
458:
445:
444:
414:
409:
405:
392:Institutions
371:
284:
266:
257:
247:
240:
233:
226:
214:
194:
164:
155:
145:
138:
131:
124:
112:
101:
84:verification
77:
50:
43:
37:
36:Please help
33:
1384:1947 births
1218:: 137–143.
618:Alpha-EM ⊃
347:Nationality
1378:Categories
830:Kybernetik
791:References
636:clustering
490:, and the
328:1947-03-23
230:newspapers
197:references
158:March 2012
128:newspapers
39:improve it
1329:0090-6778
1294:0018-9448
1259:0096-3518
1096:1045-9227
1046:1045-9227
998:1053-587X
955:0018-9448
901:0340-1200
850:0023-5946
260:June 2023
80:citations
45:talk page
1104:18252433
1054:18263462
1006:34883770
866:31189652
762:Archived
622:⊃ basic
350:Japanese
339:Yokohama
106:libelous
978:Bibcode
917:5211589
858:4853437
434:Website
341:, Japan
244:scholar
142:scholar
1327:
1292:
1257:
1193:
1160:
1102:
1094:
1052:
1044:
1004:
996:
953:
915:
909:999955
907:
899:
864:
856:
848:
777:1992:
770:1998:
757:2001:
744:2002:
724:2008:
718:2013:
712:2014:
706:2015:
700:2016:
653:: The
620:log-EM
514:Career
401:Thesis
378:Fields
246:
239:
232:
225:
217:
144:
137:
130:
123:
115:
1002:S2CID
913:S2CID
862:S2CID
728:from
634:; or
251:JSTOR
237:books
149:JSTOR
135:books
73:This
1369:IEEE
1325:ISSN
1290:ISSN
1255:ISSN
1191:ISBN
1158:ISBN
1100:PMID
1092:ISSN
1050:PMID
1042:ISSN
994:ISSN
951:ISSN
905:PMID
897:ISSN
854:PMID
846:ISSN
734:IEEE
732:and
551:Work
322:Born
223:news
121:news
82:for
1367:at
1317:doi
1282:doi
1247:doi
1220:doi
1216:164
1183:doi
1150:doi
1127:doi
1084:doi
1034:doi
986:doi
943:doi
889:doi
838:doi
730:ACM
691:).
608:).
199:to
1380::
1323:.
1313:30
1311:.
1288:.
1278:27
1276:.
1253:.
1243:28
1241:.
1214:.
1189:.
1156:.
1123:18
1121:.
1098:.
1090:.
1078:.
1062:^
1048:.
1040:.
1028:.
1014:^
1000:.
992:.
984:.
974:65
972:.
949:.
939:49
937:.
925:^
911:.
903:.
895:.
885:24
883:.
860:.
852:.
844:.
834:15
832:.
638:).
632:VQ
630:,
571:.
547:.
522:.
510:.
486:,
463:.
456:.
330:)
210:.
93:.
48:.
1345:.
1331:.
1319::
1296:.
1284::
1261:.
1249::
1226:.
1222::
1199:.
1185::
1166:.
1152::
1133:.
1129::
1106:.
1086::
1080:9
1056:.
1036::
1030:7
1008:.
988::
980::
957:.
945::
919:.
891::
868:.
840::
748:.
683:.
626:(
326:(
291:)
285:(
273:)
267:(
262:)
258:(
248:·
241:·
234:·
227:·
204:.
171:)
165:(
160:)
156:(
146:·
139:·
132:·
125:·
108:.
87:.
55:)
51:(
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.