1378:
1343:
350:. Causal mechanisms in the world give rise to statistical dependencies as epiphenomena, but only the latter are exploited by popular machine learning algorithms. Knowledge about causal structures and mechanisms is useful by letting us predict not only future data coming from the same source, but also the effect of interventions in a system, and by facilitating transfer of detected regularities to new situations.
428:
With Alex Smola, Schölkopf co-founded the series of
Machine Learning Summer Schools. He also co-founded a Cambridge-Tübingen PhD Programme and the Max Planck-ETH Center for Learning Systems. In 2016, he co-founded the Cyber Valley research consortium. He participated in the IEEE Global Initiative on
845:
P. Daniusis, D. Janzing, J. Mooij, J. Zscheischler, B. Steudel, K. Zhang, and B. Schölkopf. Inferring deterministic causal relations. In P. Grünwald and P. Spirtes, editors, 26th
Conference on Uncertainty in Artificial Intelligence, pages 143–150, Corvallis, OR, 2010. AUAI Press. Best student paper
816:
D. Janzing, P. Hoyer, and B. Schölkopf. Telling cause from effect based on high-dimensional observations. In J. Fu ̈rnkranz and T. Joachims, editors, Proceedings of the 27th
International Conference on Machine Learning, pages 479–486, Madison, WI, USA, 2010. International Machine Learning
958:
K. Zhang, B. Schölkopf, K. Muandet, and Z. Wang. Domain adaptation under target and conditional shift. In S. Dasgupta and D. McAllester, editors, Proceedings of the 30th
International Conference on Machine Learning, volume 28 of JMLR Workshop and Conference Proceedings, pages 819–827,
806:
P. O. Hoyer, D. Janzing, J. M. Mooij, J. Peters, and B. Schölkopf. Nonlinear causal discovery with additive noise models. In D. Koller, D. Schuurmans, Y. Bengio, and L. Bottou, editors, Advances in Neural
Information Processing Systems 21, pages 689–696, Red Hook, NY, USA, 2009.
796:
B. Schölkopf, D. Janzing, J. Peters, E. Sgouritsa, K. Zhang, and J. Mooij. On causal and anticausal learning. In J. Langford and J. Pineau, editors, Proceedings of the 29th
International Conference on Machine Learning (ICML), pages 1255–1262, New York, NY, USA, 2012.
756:
S. Harmeling, M. Hirsch, and B. Schölkopf. On a link between kernel mean maps and
Fraunhofer diffraction, with an application to super-resolution beyond the diffraction limit. In Computer Vision and Pattern Recognition (CVPR), pages 1083–1090. IEEE,
372:
2017. He assayed how to exploit underlying causal structures in order to make machine learning methods more robust with respect to distribution shifts and systematic errors, the latter leading to the discovery of a number of new exoplanets including
692:
Chapelle and B. Schölkopf. Incorporating invariances in nonlinear SVMs. In T. G. Dietterich, S. Becker, and Z. Ghahramani, editors, Advances in Neural
Information Processing Systems 14, pages 609–616, Cambridge, MA, USA, 2002. MIT
306:
can be generalized to a nonlinear setting by means of what is known as reproducing kernels. Another significant observation was that the data on which the kernel is defined need not be vectorial, as long as the kernel
826:
J.M. Mooij, J. Peters, D. Janzing, J. Zscheischler, and B. Schölkopf. Distinguishing cause from effect using observational data: methods and benchmarks. Journal of
Machine Learning Research, 17(32):1–102,
444:, Carl Rasmussen, Matthias Hein, Arthur Gretton, Gunnar Rätsch, Matthias Bethge, Stefanie Jegelka, Jason Weston, Olivier Bousquet, Olivier Chapelle, Joaquin Quinonero-Candela, and Sebastian Nowozin.
738:
B. Sriperumbudur, A. Gretton, K. Fukumizu, B. Schölkopf and G. Lanckriet. Hilbert Space
Embeddings and Metrics on Probability Measures. Journal of Machine Learning Research, 11: 1517—1561, 2010
1548:
1074:
D. Foreman-Mackey, B. T. Montet, D. W. Hogg, T. D. Morton, D. Wang, and B. Schölkopf. A systematic search for transiting planets in the K2 data. The Astrophysical Journal, 806(2), 2015
318:
Developing kernel PCA, Schölkopf extended it to extract invariant features and to design invariant kernels and showed how to view other major dimensionality reduction methods such as
775:
A. Gretton, O. Bousquet, A. J. Smola and B. Schölkopf. Measuring Statistical Dependence with Hilbert-Schmidt Norms. Algorithmic Learning Theory: 16th International Conference, 2005b
711:
B. Schölkopf, J. C. Platt, J. Shawe-Taylor, A. J. Smola, and R. C. Williamson. Estimating the support of a high-dimensional distribution. Neural Computation, 13(7):1443–1471, 2001b
330:, have solutions taking the form of kernel expansions on the training data, thus reducing an infinite dimensional optimization problem to a finite dimensional one. He co-developed
1553:
322:. In further work with Alex Smola and others, he extended the SVM method to regression and classification with pre-specified sparsity and quantile/support estimation. He proved a
784:
A. Gretton, K. Fukumizu, C.H. Teo, L. Song, B. Schölkopf and A. J. Smola. A Kernel Statistical Test of Independence. Advances in Neural Information Processing Systems 20, 2007
729:
A. J. Smola and A. Gretton and L. Song and B. Schölkopf. A Hilbert Space Embedding for Distributions. Algorithmic Learning Theory: 18th International Conference: 13—31, 2007
720:
A. Gretton, K. Borgwardt, M. Rasch, B. Schölkopf and A. Smola. A Kernel Method for the Two-Sample-Problem. Advances in Neural Information Processing Systems 19: 513—520, 2007
360:
Around 2010, Schölkopf began to explore how to use causality for machine learning, exploiting assumptions of independence of mechanisms and invariance. His early work on
1293:
766:
A. Gretton, R. Herbrich, A. J. Smola, O. Bousquet, and B. Schölkopf. Kernel methods for measuring independence. Journal of Machine Learning Research, 6:2075–2129, 2005a
315:, encompassing SVMs and many other algorithms. Kernel methods are now textbook knowledge and one of the major machine learning paradigms in research and applications.
836:
J. Peters, JM. Mooij, D. Janzing, and B. Schölkopf. Causal discovery with continuous additive noise models. Journal of Machine Learning Research, 15:2009–2053, 2014
274:
353:
Schölkopf and co-workers addressed (and in certain settings solved) the problem of causal discovery for the two-variable setting and connected causality to
190:
319:
1518:
302:, Schölkopf and coauthors argued that SVMs are a special case of a much larger class of methods, and all algorithms that can be expressed in terms of
1217:
1558:
1405:
1016:
Schölkopf, Bernhard; Hogg, David W.; Wang, Dun; Foreman-Mackey, Daniel; Janzing, Dominik; Simon-Gabriel, Carl-Johann; Peters, Jonas (5 July 2016).
747:
A. Gretton, K. Borgwardt, M. Rasch, B. Schölkopf and A. J. Smola. A Kernel Two-Sample Test. Journal of Machine Learning Research, 13: 723—773, 2012
1543:
418:
138:
472:
422:
250:
159:
702:
B. Schölkopf, A. J. Smola, R. C. Williamson, and P. L. Bartlett. New support vector algorithms. Neural Computation, 12(5):1207–1245, 2000a
1563:
1538:
1583:
475:
in the Information and Communication Technologies category. He was the first scientist working in Europe to receive this award.
1319:
1568:
1513:
571:
492:
1398:
433:
417:. In 2001, following positions in Berlin, Cambridge and New York, he founded the Department for Empirical Inference at the
679:
Schölkopf, P. Simard, A. J. Smola, and V. Vapnik. Prior knowledge in support vector kernels. In M. Jordan, M. Kearns, and
1508:
1141:
1084:
1523:
331:
683:, editors, Advances in Neural Information Processing Systems 10, pages 640–646, Cambridge, MA, USA, 1998d. MIT Press
1573:
327:
1235:
410:
270:
132:
1578:
1391:
447:
As of late 2023, Schölkopf is also a scientific advisor to French research group Kyutai which is being funded by
421:, which grew into a leading center for research in machine learning. In 2011, he became founding director at the
103:
1358:
241:(born 20 February 1968) is a German computer scientist known for his work in machine learning, especially on
377:, which was subsequently found to contain water vapour in its atmosphere, a first for an exoplanet in the
468:
437:
414:
389:
Schölkopf studied mathematics, physics, and philosophy in Tübingen and London. He was supported by the
1294:"Kyutai is a French AI research lab with a $ 330 million budget that will make everything open source"
266:
51:
905:
Schölkopf, Bernhard; Janzing, Dominik; Peters, Jonas; Sgouritsa, Eleni; Zhang, Kun (27 June 2012).
332:
kernel embeddings of distributions methods to represent probability distributions in Hilbert Spaces
1533:
335:
291:
591:
261:, where he heads the Department of Empirical Inference. He is also an affiliated professor at
195:
1105:
354:
326:
implying that SVMs, kernel PCA, and most other kernel algorithms, regularized by a norm in a
1528:
1029:
394:
45:
536:
8:
1377:
1369:
927:
323:
1348:
1033:
436:, a journal he helped found, being part of a mass resignation of the editorial board of
1052:
1017:
998:
887:
869:
662:
623:
541:
441:
223:
1480:
1462:
1320:"Bernhard Schölkopf receives Frontiers of Knowledge Award | Empirical Inference"
1057:
990:
666:
615:
567:
891:
452:
440:. He is among the world’s most cited computer scientists. Alumni of his lab include
100:
J. K. Aggarwal Prize of the International Association for Pattern Recognition (2006)
1456:
1444:
1047:
1037:
1002:
982:
879:
654:
627:
607:
531:
523:
413:(with Stefan Jähnichen). His thesis, defended in 1997, won the annual award of the
347:
311:
is positive definite. Both insights together led to the foundation of the field of
218:
182:
84:
74:
393:
and won the Lionel Cooper Memorial Prize for the best M.Sc. in Mathematics at the
1474:
1432:
1123:
545:
406:
390:
361:
202:
108:
Academy Prize of the Berlin-Brandenburg Academy of Sciences and Humanities (2012)
364:
was exposed to a wider machine learning audience during his Posner lecture at
1426:
1373:
1274:
857:
611:
378:
312:
295:
242:
79:
658:
527:
1502:
1486:
1256:
883:
619:
595:
123:
1042:
262:
1468:
1450:
1414:
1061:
994:
456:
111:
970:
642:
511:
1383:
448:
308:
303:
129:
Causality in Statistics Education Award, American Statistical Association
254:
680:
299:
906:
402:
246:
57:
986:
298:
pattern recognition benchmark at the time. With the introduction of
117:
Member of the German National Academy of Science (Leopoldina) (2017)
1257:"World's Top Computer Scientists: H-Index Computer Science Ranking"
1199:
874:
365:
258:
1015:
904:
643:"A Tutorial on Support Vector Machines for Pattern Recognition"
398:
374:
166:
945:
120:
Fellow of the ACM (Association for Computing Machinery) (2018)
1549:
Members of the German National Academy of Sciences Leopoldina
1180:
596:"Nonlinear Component Analysis as a Kernel Eigenvalue Problem"
1106:"TU Berlin – Medieninformation Nr. 209 – 17. September 1998"
369:
858:"Causal Inference Using the Algorithmic Markov Condition"
471:
and, shared with Isabelle Guyon and Vladimir Vapnik, the
856:
Janzing, Dominik; Schölkopf, Bernhard (6 October 2010).
275:
European Laboratory for Learning and Intelligent Systems
1554:
2017 fellows of the Association for Computing Machinery
510:
Decoste, Dennis; Schölkopf, Bernhard (1 January 2002).
589:
346:
Starting in 2005, Schölkopf turned his attention to
1162:
294:methods achieving world record performance on the
1018:"Modeling confounding by half-sibling regression"
338:as well as applications to independence testing.
1500:
855:
509:
1085:"Curriculum Vitae Prof. Dr. Bernhard Schölkopf"
1022:Proceedings of the National Academy of Sciences
419:Max Planck Institute for Biological Cybernetics
1149:The Science Magazine of the Max Planck Society
1399:
409:, who became co-adviser of his PhD thesis at
139:BBVA Foundation Frontiers of Knowledge Awards
1324:Max Planck Institute for Intelligent Systems
1200:"Max Planck ETH Center for Learning Systems"
1142:"Prescriptions for the Medicine of Tomorrow"
914:International Conference of Machine Learning
512:"Training Invariant Support Vector Machines"
473:BBVA Foundation Frontiers of Knowledge Award
423:Max Planck Institute for Intelligent Systems
251:Max Planck Institute for Intelligent Systems
160:Max Planck Institute for Intelligent Systems
384:
1519:German artificial intelligence researchers
1413:
1406:
1392:
1376:
566:. GMD-Berichte. München Wien: Oldenbourg.
1051:
1041:
968:
873:
561:
535:
493:"Causality in Statistics Education Award"
1163:"Machine Learning Summer Schools – MLSS"
946:"Causal Learning --- Bernhard Schölkopf"
641:Burges, Christopher J.C. (1 June 1998).
1559:Gottfried Wilhelm Leibniz Prize winners
969:Schölkopf, Bernhard (6 February 2015).
862:IEEE Transactions on Information Theory
792:
790:
590:Schölkopf, Bernhard; Smola, Alexander;
432:Schölkopf is co-editor-in-Chief of the
1501:
1291:
640:
368:2011, as well as in a keynote talk at
1387:
1544:Technische Universität Berlin alumni
1317:
1197:
948:. 15 October 2017 – via Vimeo.
787:
585:
583:
557:
555:
434:Journal of Machine Learning Research
405:in New Jersey, where he worked with
1292:Dillet, Romain (17 November 2023).
907:"On Causal and Anticausal Learning"
647:Data Mining and Knowledge Discovery
13:
1564:Alumni of the University of London
1181:"Cambridge Machine Learning Group"
928:"From kernels to causal inference"
14:
1595:
1334:
580:
552:
285:
1341:
1185:Cambridge Machine Learning Group
1110:archiv.pressestelle.tu-berlin.de
328:reproducing kernel Hilbert space
104:Max Planck Research Award (2011)
34:February 1968 (age 56)
1311:
1285:
1267:
1249:
1228:
1210:
1191:
1173:
1155:
1134:
1116:
1098:
1077:
1068:
1009:
962:
952:
938:
920:
898:
849:
839:
830:
820:
810:
800:
778:
769:
760:
750:
741:
732:
723:
714:
467:Schölkopf’s awards include the
320:LLE and Isomap as special cases
60:(1997, PhD in Computer Science)
1584:Max Planck Institute directors
705:
696:
686:
673:
634:
537:11858/00-001M-0000-0013-E06A-A
503:
485:
415:German Informatics Association
401:in Physics, and then moved to
1:
1539:University of Tübingen alumni
478:
271:Technische Universität Berlin
133:Körber European Science Prize
1569:Academic staff of ETH Zurich
1514:Machine learning researchers
562:Schölkopf, Bernhard (1997).
429:"Ethically Aligned Design".
341:
265:, honorary professor at the
7:
1005:– via www.nature.com.
280:
10:
1600:
1509:German computer scientists
1236:"Ethically Aligned Design"
1124:"History of the Institute"
669:– via Springer Link.
612:10.1162/089976698300017467
548:– via Springer Link.
469:Royal Society Milner Award
438:Machine Learning (journal)
249:. He is a director at the
48:(1992, MSc in Mathematics)
1524:Max Planck Society people
1422:
971:"Learning to see and act"
462:
232:
211:
181:
165:
155:
148:
93:
67:
54:(1994, Diplom in Physics)
38:
30:
23:
16:German computer scientist
1372:publications indexed by
1128:www.kyb.tuebingen.mpg.de
894:– via IEEE Xplore.
884:10.1109/TIT.2010.2060095
385:Education and employment
172:Support Vector Learning
1574:Scientists at Bell Labs
1279:people.tuebingen.mpg.de
1204:cls-staging.is.localnet
1043:10.1073/pnas.1511656113
659:10.1023/A:1009715923555
564:Support vector learning
528:10.1023/A:1012454411458
1579:Studienstiftung alumni
1261:www.guide2research.com
336:Fraunhofer diffraction
273:, and chairman of the
267:University of Tübingen
52:University of Tübingen
355:Kolmogorov complexity
1222:Baden-Württemberg.de
1198:Williams, Jonathan.
592:Müller, Klaus-Robert
395:University of London
290:Schölkopf developed
46:University of London
1245:. 13 December 2016.
1224:. 15 December 2016.
1034:2016PNAS..113.7391S
324:representer theorem
1439:Bernhard Schölkopf
1370:Bernhard Schölkopf
1359:Bernhard Schölkopf
600:Neural Computation
442:Ulrike von Luxburg
239:Bernhard Schölkopf
224:Ulrike von Luxburg
25:Bernhard Schölkopf
1496:
1495:
1481:Zoubin Ghahramani
1463:Marta Kwiatkowska
1028:(27): 7391–7398.
981:(7540): 486–487.
932:videolectures.net
868:(10): 5168–5194.
573:978-3-486-24632-2
397:. He completed a
236:
235:
212:Doctoral students
150:Scientific career
1591:
1457:Andrew Zisserman
1445:Thomas Henzinger
1408:
1401:
1394:
1385:
1384:
1380:
1345:
1344:
1328:
1327:
1315:
1309:
1308:
1306:
1304:
1289:
1283:
1282:
1271:
1265:
1264:
1253:
1247:
1246:
1240:
1232:
1226:
1225:
1214:
1208:
1207:
1195:
1189:
1188:
1177:
1171:
1170:
1159:
1153:
1152:
1146:
1138:
1132:
1131:
1120:
1114:
1113:
1102:
1096:
1095:
1089:
1081:
1075:
1072:
1066:
1065:
1055:
1045:
1013:
1007:
1006:
966:
960:
956:
950:
949:
942:
936:
935:
924:
918:
917:
911:
902:
896:
895:
877:
853:
847:
843:
837:
834:
828:
824:
818:
814:
808:
804:
798:
794:
785:
782:
776:
773:
767:
764:
758:
754:
748:
745:
739:
736:
730:
727:
721:
718:
712:
709:
703:
700:
694:
690:
684:
677:
671:
670:
638:
632:
631:
606:(5): 1299–1319.
587:
578:
577:
559:
550:
549:
539:
516:Machine Learning
507:
501:
500:
489:
348:causal inference
334:, with links to
219:Stefanie Jegelka
199:
191:Stefan Jähnichen
183:Doctoral advisor
177:
85:Causal Inference
75:Machine Learning
21:
20:
1599:
1598:
1594:
1593:
1592:
1590:
1589:
1588:
1499:
1498:
1497:
1492:
1475:Cordelia Schmid
1433:Serge Abiteboul
1418:
1412:
1366:
1365:
1364:
1346:
1342:
1337:
1332:
1331:
1318:Williams, Jon.
1316:
1312:
1302:
1300:
1290:
1286:
1273:
1272:
1268:
1255:
1254:
1250:
1238:
1234:
1233:
1229:
1216:
1215:
1211:
1196:
1192:
1179:
1178:
1174:
1161:
1160:
1156:
1144:
1140:
1139:
1135:
1122:
1121:
1117:
1104:
1103:
1099:
1087:
1083:
1082:
1078:
1073:
1069:
1014:
1010:
987:10.1038/518486a
967:
963:
957:
953:
944:
943:
939:
926:
925:
921:
909:
903:
899:
854:
850:
844:
840:
835:
831:
825:
821:
815:
811:
805:
801:
795:
788:
783:
779:
774:
770:
765:
761:
755:
751:
746:
742:
737:
733:
728:
724:
719:
715:
710:
706:
701:
697:
691:
687:
678:
674:
639:
635:
594:(1 July 1998).
588:
581:
574:
560:
553:
508:
504:
491:
490:
486:
481:
465:
407:Vladimir Vapnik
391:Studienstiftung
387:
362:causal learning
344:
288:
283:
228:
207:
203:Vladimir Vapnik
193:
175:
144:
89:
63:
39:Alma mater
26:
17:
12:
11:
5:
1597:
1587:
1586:
1581:
1576:
1571:
1566:
1561:
1556:
1551:
1546:
1541:
1536:
1531:
1526:
1521:
1516:
1511:
1494:
1493:
1491:
1490:
1484:
1478:
1472:
1466:
1460:
1454:
1448:
1442:
1436:
1430:
1427:Gordon Plotkin
1423:
1420:
1419:
1411:
1410:
1403:
1396:
1388:
1382:
1381:
1374:Google Scholar
1347:
1340:
1339:
1338:
1336:
1335:External links
1333:
1330:
1329:
1310:
1284:
1266:
1248:
1227:
1209:
1190:
1172:
1154:
1133:
1115:
1097:
1076:
1067:
1008:
961:
951:
937:
919:
897:
848:
838:
829:
819:
809:
799:
786:
777:
768:
759:
749:
740:
731:
722:
713:
704:
695:
685:
672:
653:(2): 121–167.
633:
579:
572:
551:
522:(1): 161–190.
502:
497:www.amstat.org
483:
482:
480:
477:
464:
461:
459:, and others.
453:Rodolphe Saadé
386:
383:
379:habitable zone
343:
340:
313:kernel methods
287:
286:Kernel methods
284:
282:
279:
243:kernel methods
234:
233:
230:
229:
227:
226:
221:
215:
213:
209:
208:
206:
205:
200:
187:
185:
179:
178:
169:
163:
162:
157:
153:
152:
146:
145:
143:
142:
136:
130:
127:
121:
118:
115:
109:
106:
101:
97:
95:
91:
90:
88:
87:
82:
80:Kernel Methods
77:
71:
69:
68:Known for
65:
64:
62:
61:
55:
49:
42:
40:
36:
35:
32:
28:
27:
24:
15:
9:
6:
4:
3:
2:
1596:
1585:
1582:
1580:
1577:
1575:
1572:
1570:
1567:
1565:
1562:
1560:
1557:
1555:
1552:
1550:
1547:
1545:
1542:
1540:
1537:
1535:
1534:Living people
1532:
1530:
1527:
1525:
1522:
1520:
1517:
1515:
1512:
1510:
1507:
1506:
1504:
1488:
1487:Yvonne Rogers
1485:
1482:
1479:
1476:
1473:
1470:
1467:
1464:
1461:
1458:
1455:
1452:
1449:
1446:
1443:
1440:
1437:
1434:
1431:
1428:
1425:
1424:
1421:
1416:
1409:
1404:
1402:
1397:
1395:
1390:
1389:
1386:
1379:
1375:
1371:
1368:
1367:
1362:
1361:
1360:
1354:
1350:
1325:
1321:
1314:
1299:
1295:
1288:
1280:
1276:
1270:
1262:
1258:
1252:
1244:
1237:
1231:
1223:
1219:
1213:
1205:
1201:
1194:
1186:
1182:
1176:
1168:
1164:
1158:
1150:
1143:
1137:
1129:
1125:
1119:
1111:
1107:
1101:
1093:
1086:
1080:
1071:
1063:
1059:
1054:
1049:
1044:
1039:
1035:
1031:
1027:
1023:
1019:
1012:
1004:
1000:
996:
992:
988:
984:
980:
976:
972:
965:
955:
947:
941:
933:
929:
923:
915:
908:
901:
893:
889:
885:
881:
876:
871:
867:
863:
859:
852:
842:
833:
823:
813:
803:
793:
791:
781:
772:
763:
753:
744:
735:
726:
717:
708:
699:
689:
682:
676:
668:
664:
660:
656:
652:
648:
644:
637:
629:
625:
621:
617:
613:
609:
605:
601:
597:
593:
586:
584:
575:
569:
565:
558:
556:
547:
543:
538:
533:
529:
525:
521:
517:
513:
506:
498:
494:
488:
484:
476:
474:
470:
460:
458:
454:
450:
445:
443:
439:
435:
430:
426:
424:
420:
416:
412:
408:
404:
400:
396:
392:
382:
380:
376:
371:
367:
363:
358:
356:
351:
349:
339:
337:
333:
329:
325:
321:
316:
314:
310:
305:
301:
297:
293:
278:
276:
272:
268:
264:
260:
256:
252:
248:
244:
240:
231:
225:
222:
220:
217:
216:
214:
210:
204:
201:
197:
192:
189:
188:
186:
184:
180:
173:
170:
168:
164:
161:
158:
154:
151:
147:
140:
137:
134:
131:
128:
125:
124:Leibniz Prize
122:
119:
116:
113:
110:
107:
105:
102:
99:
98:
96:
92:
86:
83:
81:
78:
76:
73:
72:
70:
66:
59:
56:
53:
50:
47:
44:
43:
41:
37:
33:
29:
22:
19:
1469:Eugene Myers
1451:Xavier Leroy
1438:
1415:Milner Award
1357:
1356:
1355:profile for
1352:
1323:
1313:
1301:. Retrieved
1297:
1287:
1278:
1269:
1260:
1251:
1242:
1230:
1221:
1212:
1203:
1193:
1184:
1175:
1166:
1157:
1148:
1136:
1127:
1118:
1109:
1100:
1094:(in German).
1091:
1079:
1070:
1025:
1021:
1011:
978:
974:
964:
954:
940:
931:
922:
913:
900:
865:
861:
851:
841:
832:
822:
812:
802:
780:
771:
762:
752:
743:
734:
725:
716:
707:
698:
688:
675:
650:
646:
636:
603:
599:
563:
519:
515:
505:
496:
487:
466:
457:Eric Schmidt
446:
431:
427:
388:
359:
352:
345:
317:
304:dot products
289:
238:
237:
171:
156:Institutions
149:
112:Milner Award
18:
1529:1968 births
449:Xavier Niel
309:Gram matrix
194: [
1503:Categories
1298:TechCrunch
1092:Leopoldina
479:References
300:kernel PCA
263:ETH Zürich
1417:laureates
1218:"Service"
875:0804.3678
797:Omnipress
667:221627509
620:0899-7667
411:TU Berlin
403:Bell Labs
342:Causality
277:(ELLIS).
247:causality
58:TU Berlin
1275:"Alumni"
1062:27382154
995:25719660
892:11867432
681:S. Solla
281:Research
255:Tübingen
1351:has an
1349:Scholia
1303:16 June
1167:mlss.cc
1151:. 2011.
1053:4941423
1030:Bibcode
1003:4461791
817:Society
628:6674407
366:NeurIPS
259:Germany
1489:(2022)
1483:(2021)
1477:(2020)
1471:(2019)
1465:(2018)
1459:(2017)
1453:(2016)
1447:(2015)
1441:(2014)
1435:(2013)
1429:(2012)
1353:author
1060:
1050:
1001:
993:
975:Nature
890:
807:Curran
665:
626:
618:
570:
544:
463:Awards
399:Diplom
375:K2-18b
176:(1997)
174:
167:Thesis
141:(2020)
135:(2019)
126:(2018)
114:(2014)
94:Awards
1239:(PDF)
1145:(PDF)
1088:(PDF)
999:S2CID
910:(PDF)
888:S2CID
870:arXiv
846:award
693:Press
663:S2CID
624:S2CID
546:85843
542:S2CID
296:MNIST
198:]
1305:2024
1243:IEEE
1058:PMID
991:PMID
959:2013
827:2016
757:2013
616:ISSN
568:ISBN
370:ICML
269:and
245:and
31:Born
1048:PMC
1038:doi
1026:113
983:doi
979:518
880:doi
655:doi
608:doi
532:hdl
524:doi
292:SVM
253:in
1505::
1322:.
1296:.
1277:.
1259:.
1241:.
1220:.
1202:.
1183:.
1165:.
1147:.
1126:.
1108:.
1090:.
1056:.
1046:.
1036:.
1024:.
1020:.
997:.
989:.
977:.
973:.
930:.
912:.
886:.
878:.
866:56
864:.
860:.
789:^
661:.
649:.
645:.
622:.
614:.
604:10
602:.
598:.
582:^
554:^
540:.
530:.
520:46
518:.
514:.
495:.
455:,
451:,
425:.
381:.
357:.
257:,
196:de
1407:e
1400:t
1393:v
1363:.
1326:.
1307:.
1281:.
1263:.
1206:.
1187:.
1169:.
1130:.
1112:.
1064:.
1040::
1032::
985::
934:.
916:.
882::
872::
657::
651:2
630:.
610::
576:.
534::
526::
499:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.