49:
179:
290:
after having led the
Institute of Bioinformatics from 2006 to 2018. In 2017 he became the head of the Linz Institute of Technology (LIT) AI Lab. Hochreiter is also a founding director of the Institute of Advanced Research in Artificial Intelligence (IARAI). Previously, he was at
1063:
Hochreiter, Sepp; Bodenhofer, Ulrich; Heusel, Martin; Mayr, Andreas; Mitterecker, Andreas; Kasim, Adetayo; Khamiakova, Tatsiana; Van Sanden, Suzy; Lin, Dan; Talloen, Willem; Bijnens, Luc; Göhlmann, Hinrich W. H.; Shkedy, Ziv; Clevert, Djork-Arné (2010-06-15).
999:
Ramsauer, H.; Schäfl, B.; Lehner, J.; Seidl, P.; Widrich, M.; Gruber, L.; Holzleitner, M.; Pavlović, M.; Sandve, G. K.; Greiff, V.; Kreil, D.; Kopp, M.; Klambauer, G.; Brandstetter, J.; Hochreiter, S. (2020). "Hopfield
Networks is All You Need".
1021:
Widrich, M.; Schäfl, B.; Ramsauer, H.; Pavlović, M.; Gruber, L.; Holzleitner, M.; Brandstetter, J.; Sandve, G. K.; Greiff, V.; Hochreiter, S.; Klambauer, G. (2020). "Modern
Hopfield Networks and Attention for Immune Repertoire Classification".
446:(SVM), the "Potential Support Vector Machine" (PSVM), which can be applied to non-square kernel matrices and can be used with kernels that are not positive definite. Hochreiter and his collaborators have applied PSVM to
1440:
1445:
1430:
355:(LSTM) neural network architecture in his diploma thesis in 1991 leading to the main publication in 1997. LSTM overcomes the problem of numerical instability in training
1046:
Making the world differentiable: On Using Fully
Recurrent Self-Supervised Neural Networks for Dynamic Reinforcement Learning and Planning in Non-Stationary Environments
678:
Arjona-Medina, J. A.; Gillhofer, M.; Widrich, M.; Unterthiner, T.; Hochreiter, S. (2018). "RUDDER: Return
Decomposition for Delayed Rewards".
1435:
1333:
1273:
625:
100:
1313:
1290:
144:
283:
1353:
1415:
262:
200:
193:
323:
292:
1115:"HapFABIA: Identification of very short segments of identity by descent characterized by rare variants in large sequencing data"
131:
395:
factor networks (RFNs) for sparse coding which have been applied in bioinformatics and genetics. Hochreiter introduced modern
243:
1425:
422:
300:
296:
808:
215:
1390:
822:
222:
392:
699:
Hochreiter, S. (1998). "The
Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions".
360:
189:
1420:
356:
229:
363:). In 2007, Hochreiter and others successfully applied LSTM with an optimized architecture to very fast protein
1450:
211:
1410:
1212:
747:
603:
443:
403:
352:
327:
319:
742:
Hochreiter, S.; Bengio, Y.; Frasconi, P.; Schmidhuber, J. (2000). Kolen, J. F.; Kremer, S. C. (eds.).
1405:
1052:(Technical report). Technical University Munich, Institute of Computer Science. FKI-126-90 (revised).
1217:
752:
593:
Hochreiter, S.; Younger, A. S.; Conwell, P. R. (2001). "Learning to Learn Using
Gradient Descent".
418:
1291:"Classification and Feature Selection on Matrix Data with Application to Gene-Expression Analysis"
1238:
1044:
1023:
1001:
930:
905:
886:
724:
679:
639:
608:
575:
368:
279:
458:
Hochreiter was awarded the IEEE CIS Neural
Networks Pioneer Prize in 2021 for his work on LSTM.
904:
Clevert, D.-A.; Mayr, A.; Unterthiner, T.; Hochreiter, S. (2015). "Rectified Factor
Networks".
837:
662:
Implementierung und
Anwendung eines neuronalen Echtzeit-Lernalgorithmus fĂĽr reaktive Umgebungen
1329:
1269:
1230:
1185:
1144:
1095:
981:
878:
790:
746:. A Field Guide to Dynamical Recurrent Networks. New York City: IEEE Press. pp. 237–244.
716:
631:
621:
567:
447:
364:
1339:
1298:
236:
1321:
1261:
1222:
1175:
1134:
1126:
1085:
1077:
971:
963:
870:
780:
708:
613:
559:
396:
307:
156:
117:
436:
429:
426:
410:
161:
399:
with continuous states and applied them to the task of immune repertoire classification.
661:
303:. He is a chair of the Critical Assessment of Massive Data Analysis (CAMDA) conference.
1139:
1114:
1090:
1065:
976:
951:
594:
528:
388:
335:
315:
121:
1399:
1325:
311:
1242:
1180:
1163:
1081:
967:
785:
768:
728:
643:
579:
414:
372:
331:
79:
890:
744:
Gradient flow in recurrent nets: the difficulty of learning long-term dependencies
1265:
1260:. Feature Extraction, Studies in Fuzziness and Soft Computing. pp. 419–438.
1203:
Hochreiter, S.; Obermayer, K. (2006). "Support Vector Machines for Dyadic Data".
1226:
376:
178:
75:
48:
31:
563:
1354:"Sepp Hochreiter receives IEEE CIS Neural Networks Pioneer Award 2021 - IARAI"
712:
1386:
1381:
720:
635:
617:
536:(diploma thesis). Technical University Munich, Institute of Computer Science.
503:
20th International Conference on Critical Assessment of Massive Data Analysis
874:
387:
Beyond LSTM, Hochreiter has developed "Flat Minimum Search" to increase the
1234:
1189:
1148:
1099:
985:
794:
701:
International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems
1130:
882:
571:
406:
on actor-critic systems that learn by "backpropagation through a model".
17:
90:
1258:
Nonlinear Feature Selection with the Potential Support Vector Machine
950:
Clevert, D.-A.; Unterthiner, T.; Povysil, G.; Hochreiter, S. (2017).
910:
667:(Report). Technical University Munich, Institute of Computer Science.
602:. Lecture Notes in Computer Science. Vol. 2130. pp. 87–94.
138:
30:"Hochreiter" redirects here. For people with a similar surname, see
1028:
1006:
935:
684:
475:"IARAI – INSTITUTE OF ADVANCED RESEARCH IN ARTIFICIAL INTELLIGENCE"
925:
Clevert, D.-A.; Mayr, A.; Unterthiner, T.; Hochreiter, S. (2015).
550:
Hochreiter, S.; Schmidhuber, J. (1997). "Long Short-Term Memory".
282:. Since 2018 he has led the Institute for Machine Learning at the
413:
methods with application to bioinformatics, including FABIA for
287:
769:"Fast model-based protein homology detection without alignment"
433:
379:
chat app for generating response suggestion with low latency.
172:
359:(RNNs) that prevents them from learning from long sequences (
1164:"A new summarization method for affymetrix probe level data"
442:
In 2006, Hochreiter and others proposed an extension of the
474:
952:"Rectified factor networks for biclustering of omics data"
402:
Hochreiter worked with JĂĽrgen Schmidhuber in the field of
145:
Generalisierung bei neuronalen Netzen geringer Komplexität
498:
929:. Advances in Neural Information Processing Systems 29.
1295:
54th Session of the International Statistical Institute
861:
Hochreiter, S.; Schmidhuber, J. (1997). "Flat Minima".
809:"The neural networks behind Google Voice transcription"
1162:
Hochreiter, S.; Clevert, D.-A.; Obermayer, K. (2006).
1441:
Academic staff of the Technical University of Munich
409:Hochreiter has been involved in the development of
306:Hochreiter has made contributions in the fields of
155:
137:
127:
113:
96:
86:
58:
39:
1066:"FABIA: factor analysis for bicluster acquisition"
767:Hochreiter, S.; Heusel, M.; Obermayer, K. (2007).
1446:Academic staff of Johannes Kepler University Linz
450:, including gene selection for microarray data.
322:(LSTM) neural network architecture, but also in
823:"Google voice search: faster and more accurate"
530:Untersuchungen zu dynamischen neuronalen Netzen
8:
417:, HapFABIA for detecting short segments of
1431:German artificial intelligence researchers
47:
36:
1216:
1179:
1138:
1089:
1027:
1005:
975:
934:
909:
784:
751:
683:
607:
375:for transcription and search, and in the
263:Learn how and when to remove this message
655:
653:
522:
520:
518:
1318:Kernel Methods in Computational Biology
596:Artificial Neural Networks — ICANN 2001
466:
371:. LSTM networks have also been used in
1312:Hochreiter, S.; Obermayer, K. (2004).
1289:Hochreiter, S.; Obermayer, K. (2003).
1256:Hochreiter, S.; Obermayer, K. (2006).
545:
543:
318:, most notably the development of the
199:Please improve this article by adding
7:
1314:"Gene Selection for Microarray Data"
383:Other machine learning contributions
278:(born 14 February 1967) is a German
391:of neural networks and introduced
25:
836:Khaitan, Pranav (May 18, 2016).
177:
361:vanishing or exploding gradient
132:Johannes Kepler University Linz
1326:10.7551/mitpress/4057.003.0020
367:detection without requiring a
301:Technical University of Munich
297:University of Colorado Boulder
101:Technische Universität München
1:
1391:Mathematics Genealogy Project
1181:10.1093/bioinformatics/btl033
1082:10.1093/bioinformatics/btq227
968:10.1093/bioinformatics/btx226
786:10.1093/bioinformatics/btm247
423:preprocessing and summarizing
347:Long short-term memory (LSTM)
293:Technische Universität Berlin
201:secondary or tertiary sources
1436:Machine learning researchers
1266:10.1007/978-3-540-35488-8_20
1227:10.1162/neco.2006.18.6.1472
1467:
564:10.1162/neco.1997.9.8.1735
284:Johannes Kepler University
29:
1382:Home Page Sepp Hochreiter
927:Rectified Factor Networks
713:10.1142/S0218488598000094
357:recurrent neural networks
351:Hochreiter developed the
167:
106:
46:
27:German computer scientist
1416:German bioinformaticians
1043:Schmidhuber, J. (1990).
838:"Chat Smarter with Allo"
618:10.1007/3-540-44668-0_13
1113:Hochreiter, S. (2013).
875:10.1162/neco.1997.9.1.1
660:Hochreiter, S. (1991).
527:Hochreiter, S. (1991).
276:Josef "Sepp" Hochreiter
1320:. MIT Press: 319–355.
1119:Nucleic Acids Research
444:support vector machine
404:reinforcement learning
353:long short-term memory
328:reinforcement learning
320:long short-term memory
188:relies excessively on
1426:Computational biology
825:. 24 September 2015.
334:with application to
1131:10.1093/nar/gkt1013
419:identity by descent
1205:Neural Computation
863:Neural Computation
552:Neural Computation
369:sequence alignment
280:computer scientist
53:Hochreiter in 2012
1335:978-0-262-25692-6
1275:978-3-540-35487-1
1076:(12): 1520–1527.
811:. 11 August 2015.
779:(14): 1728–1736.
627:978-3-540-42486-4
448:feature selection
397:Hopfield networks
342:Scientific career
273:
272:
265:
247:
212:"Sepp Hochreiter"
171:
170:
108:Scientific career
16:(Redirected from
1458:
1421:Biostatisticians
1370:
1369:
1367:
1365:
1350:
1344:
1343:
1338:. Archived from
1309:
1303:
1302:
1297:. Archived from
1286:
1280:
1279:
1253:
1247:
1246:
1220:
1211:(6): 1472–1510.
1200:
1194:
1193:
1183:
1159:
1153:
1152:
1142:
1110:
1104:
1103:
1093:
1060:
1054:
1053:
1051:
1040:
1034:
1033:
1031:
1018:
1012:
1011:
1009:
996:
990:
989:
979:
947:
941:
940:
938:
922:
916:
915:
913:
901:
895:
894:
858:
852:
851:
849:
848:
833:
827:
826:
819:
813:
812:
805:
799:
798:
788:
764:
758:
757:
755:
739:
733:
732:
696:
690:
689:
687:
675:
669:
668:
666:
657:
648:
647:
611:
601:
590:
584:
583:
558:(8): 1735–1780.
547:
538:
537:
535:
524:
513:
512:
510:
509:
495:
489:
488:
486:
485:
471:
308:machine learning
268:
261:
257:
254:
248:
246:
205:
181:
173:
157:Doctoral advisor
151:
118:Machine learning
72:
69:14 February 1967
68:
66:
51:
37:
21:
1466:
1465:
1461:
1460:
1459:
1457:
1456:
1455:
1396:
1395:
1387:Sepp Hochreiter
1378:
1373:
1363:
1361:
1358:www.iarai.ac.at
1352:
1351:
1347:
1336:
1311:
1310:
1306:
1288:
1287:
1283:
1276:
1255:
1254:
1250:
1218:10.1.1.228.5244
1202:
1201:
1197:
1161:
1160:
1156:
1112:
1111:
1107:
1062:
1061:
1057:
1049:
1042:
1041:
1037:
1020:
1019:
1015:
998:
997:
993:
962:(14): i59–i66.
949:
948:
944:
924:
923:
919:
903:
902:
898:
860:
859:
855:
846:
844:
835:
834:
830:
821:
820:
816:
807:
806:
802:
766:
765:
761:
741:
740:
736:
698:
697:
693:
677:
676:
672:
664:
659:
658:
651:
628:
599:
592:
591:
587:
549:
548:
541:
533:
526:
525:
516:
507:
505:
497:
496:
492:
483:
481:
479:www.iarai.ac.at
473:
472:
468:
464:
456:
437:gene expression
430:DNA microarrays
427:oligonucleotide
411:factor analysis
385:
349:
344:
269:
258:
252:
249:
206:
204:
198:
194:primary sources
182:
162:Wilfried Brauer
149:
97:Alma mater
82:
73:
70:
64:
62:
54:
42:
41:Sepp Hochreiter
35:
28:
23:
22:
15:
12:
11:
5:
1464:
1462:
1454:
1453:
1451:Allianz people
1448:
1443:
1438:
1433:
1428:
1423:
1418:
1413:
1408:
1398:
1397:
1394:
1393:
1384:
1377:
1376:External links
1374:
1372:
1371:
1360:. 24 July 2020
1345:
1342:on 2012-03-25.
1334:
1304:
1301:on 2012-03-25.
1281:
1274:
1248:
1195:
1174:(8): 943–949.
1168:Bioinformatics
1154:
1105:
1070:Bioinformatics
1055:
1035:
1013:
991:
956:Bioinformatics
942:
917:
896:
853:
842:Google AI Blog
828:
814:
800:
773:Bioinformatics
759:
753:10.1.1.24.7321
734:
707:(2): 107–116.
691:
670:
649:
626:
585:
539:
514:
490:
465:
463:
460:
455:
452:
421:and FARMS for
389:generalization
384:
381:
348:
345:
343:
340:
336:bioinformatics
316:bioinformatics
271:
270:
185:
183:
176:
169:
168:
165:
164:
159:
153:
152:
141:
135:
134:
129:
125:
124:
122:bioinformatics
115:
111:
110:
104:
103:
98:
94:
93:
88:
84:
83:
74:
60:
56:
55:
52:
44:
43:
40:
26:
24:
14:
13:
10:
9:
6:
4:
3:
2:
1463:
1452:
1449:
1447:
1444:
1442:
1439:
1437:
1434:
1432:
1429:
1427:
1424:
1422:
1419:
1417:
1414:
1412:
1411:Living people
1409:
1407:
1404:
1403:
1401:
1392:
1388:
1385:
1383:
1380:
1379:
1375:
1359:
1355:
1349:
1346:
1341:
1337:
1331:
1327:
1323:
1319:
1315:
1308:
1305:
1300:
1296:
1292:
1285:
1282:
1277:
1271:
1267:
1263:
1259:
1252:
1249:
1244:
1240:
1236:
1232:
1228:
1224:
1219:
1214:
1210:
1206:
1199:
1196:
1191:
1187:
1182:
1177:
1173:
1169:
1165:
1158:
1155:
1150:
1146:
1141:
1136:
1132:
1128:
1124:
1120:
1116:
1109:
1106:
1101:
1097:
1092:
1087:
1083:
1079:
1075:
1071:
1067:
1059:
1056:
1048:
1047:
1039:
1036:
1030:
1025:
1017:
1014:
1008:
1003:
995:
992:
987:
983:
978:
973:
969:
965:
961:
957:
953:
946:
943:
937:
932:
928:
921:
918:
912:
907:
900:
897:
892:
888:
884:
880:
876:
872:
868:
864:
857:
854:
843:
839:
832:
829:
824:
818:
815:
810:
804:
801:
796:
792:
787:
782:
778:
774:
770:
763:
760:
754:
749:
745:
738:
735:
730:
726:
722:
718:
714:
710:
706:
702:
695:
692:
686:
681:
674:
671:
663:
656:
654:
650:
645:
641:
637:
633:
629:
623:
619:
615:
610:
605:
598:
597:
589:
586:
581:
577:
573:
569:
565:
561:
557:
553:
546:
544:
540:
532:
531:
523:
521:
519:
515:
504:
500:
494:
491:
480:
476:
470:
467:
461:
459:
453:
451:
449:
445:
440:
438:
435:
431:
428:
425:high-density
424:
420:
416:
412:
407:
405:
400:
398:
394:
390:
382:
380:
378:
374:
370:
366:
362:
358:
354:
346:
341:
339:
337:
333:
329:
325:
324:meta-learning
321:
317:
313:
312:deep learning
309:
304:
302:
299:, and at the
298:
294:
289:
285:
281:
277:
267:
264:
256:
245:
242:
238:
235:
231:
228:
224:
221:
217:
214: –
213:
209:
208:Find sources:
202:
196:
195:
191:
186:This article
184:
180:
175:
174:
166:
163:
160:
158:
154:
147:
146:
142:
140:
136:
133:
130:
126:
123:
119:
116:
112:
109:
105:
102:
99:
95:
92:
89:
85:
81:
77:
71:(age 57)
61:
57:
50:
45:
38:
33:
19:
1362:. Retrieved
1357:
1348:
1340:the original
1317:
1307:
1299:the original
1294:
1284:
1257:
1251:
1208:
1204:
1198:
1171:
1167:
1157:
1125:(22): e202.
1122:
1118:
1108:
1073:
1069:
1058:
1045:
1038:
1016:
994:
959:
955:
945:
926:
920:
911:1502.06464v2
899:
866:
862:
856:
845:. Retrieved
841:
831:
817:
803:
776:
772:
762:
743:
737:
704:
700:
694:
673:
609:10.1.1.5.323
595:
588:
555:
551:
529:
506:. Retrieved
502:
499:"CAMDA 2021"
493:
482:. Retrieved
478:
469:
457:
441:
415:biclustering
408:
401:
386:
373:Google Voice
350:
332:biclustering
305:
275:
274:
259:
253:October 2021
250:
240:
233:
226:
219:
207:
187:
143:
128:Institutions
107:
80:West Germany
1406:1967 births
869:(1): 1–42.
432:to analyze
377:Google Allo
87:Nationality
32:Hochreither
1400:Categories
1029:2007.13505
1007:2008.02217
936:1502.06464
847:2021-10-20
685:1806.07857
508:2021-02-13
484:2021-02-13
462:References
223:newspapers
190:references
65:1967-02-14
18:Hochreiter
1213:CiteSeerX
748:CiteSeerX
721:0218-4885
636:0302-9743
604:CiteSeerX
393:rectified
1243:26201227
1235:16764511
1190:16473874
1149:24174545
1100:20418340
986:28881961
795:17488755
729:18452318
644:52872549
365:homology
76:MĂĽhldorf
1389:at the
1140:3905877
1091:2881408
977:5870657
883:9117894
580:1915014
572:9377276
237:scholar
1364:3 June
1332:
1272:
1241:
1233:
1215:
1188:
1147:
1137:
1098:
1088:
984:
974:
891:733161
889:
881:
793:
750:
727:
719:
642:
634:
624:
606:
578:
570:
454:Awards
338:data.
239:
232:
225:
218:
210:
150:(1999)
148:
139:Thesis
114:Fields
91:German
1239:S2CID
1050:(PDF)
1024:arXiv
1002:arXiv
931:arXiv
906:arXiv
887:S2CID
725:S2CID
680:arXiv
665:(PDF)
640:S2CID
600:(PDF)
576:S2CID
534:(PDF)
295:, at
244:JSTOR
230:books
1366:2021
1330:ISBN
1270:ISBN
1231:PMID
1186:PMID
1145:PMID
1096:PMID
982:PMID
879:PMID
791:PMID
717:ISSN
632:ISSN
622:ISBN
568:PMID
330:and
314:and
288:Linz
216:news
59:Born
1322:doi
1262:doi
1223:doi
1176:doi
1135:PMC
1127:doi
1086:PMC
1078:doi
972:PMC
964:doi
871:doi
781:doi
709:doi
614:doi
560:doi
439:.
434:RNA
286:of
192:to
1402::
1356:.
1328:.
1316:.
1293:.
1268:.
1237:.
1229:.
1221:.
1209:18
1207:.
1184:.
1172:22
1170:.
1166:.
1143:.
1133:.
1123:41
1121:.
1117:.
1094:.
1084:.
1074:26
1072:.
1068:.
980:.
970:.
960:33
958:.
954:.
885:.
877:.
865:.
840:.
789:.
777:23
775:.
771:.
723:.
715:.
705:06
703:.
652:^
638:.
630:.
620:.
612:.
574:.
566:.
554:.
542:^
517:^
501:.
477:.
326:,
310:,
203:.
120:,
78:,
67:)
1368:.
1324::
1278:.
1264::
1245:.
1225::
1192:.
1178::
1151:.
1129::
1102:.
1080::
1032:.
1026::
1010:.
1004::
988:.
966::
939:.
933::
914:.
908::
893:.
873::
867:9
850:.
797:.
783::
756:.
731:.
711::
688:.
682::
646:.
616::
582:.
562::
556:9
511:.
487:.
266:)
260:(
255:)
251:(
241:·
234:·
227:·
220:·
197:.
63:(
34:.
20:)
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.
